Built site for gh-pages
This commit is contained in:
Quarto GHA Workflow Runner
@@ -1455,393 +1455,395 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<span id="cb1-936"><a href="#cb1-936" aria-hidden="true" tabindex="-1"></a><span class="fu">profiler_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-937"><a href="#cb1-937" aria-hidden="true" tabindex="-1"></a><span class="co"># Which step to start the profiler at. Useful for only capturing a few steps mid-run.</span></span>
|
||||
<span id="cb1-938"><a href="#cb1-938" aria-hidden="true" tabindex="-1"></a><span class="fu">profiler_steps_start</span><span class="kw">:</span><span class="at"> int | None = 0</span></span>
|
||||
<span id="cb1-939"><a href="#cb1-939" aria-hidden="true" tabindex="-1"></a><span class="co"># bool of whether to include tokens trainer per second in the training metrics. This</span></span>
|
||||
<span id="cb1-940"><a href="#cb1-940" aria-hidden="true" tabindex="-1"></a><span class="co"># iterates over the entire dataset once, so it takes some time.</span></span>
|
||||
<span id="cb1-939"><a href="#cb1-939" aria-hidden="true" tabindex="-1"></a><span class="co"># bool of whether to report tokens per second at the end of training. This is not</span></span>
|
||||
<span id="cb1-940"><a href="#cb1-940" aria-hidden="true" tabindex="-1"></a><span class="co"># supported with pre-training datasets.</span></span>
|
||||
<span id="cb1-941"><a href="#cb1-941" aria-hidden="true" tabindex="-1"></a><span class="fu">include_tokens_per_second</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-942"><a href="#cb1-942" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-943"><a href="#cb1-943" aria-hidden="true" tabindex="-1"></a><span class="co"># NEFT https://arxiv.org/abs/2310.05914, set this to a number (paper default is 5) to</span></span>
|
||||
<span id="cb1-944"><a href="#cb1-944" aria-hidden="true" tabindex="-1"></a><span class="co"># add noise to embeddings. Currently only supported on Llama and Mistral</span></span>
|
||||
<span id="cb1-945"><a href="#cb1-945" aria-hidden="true" tabindex="-1"></a><span class="fu">neftune_noise_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-946"><a href="#cb1-946" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-947"><a href="#cb1-947" aria-hidden="true" tabindex="-1"></a><span class="co"># Parameter controlling the relative ratio loss weight in the ORPO loss. Passed to</span></span>
|
||||
<span id="cb1-948"><a href="#cb1-948" aria-hidden="true" tabindex="-1"></a><span class="co"># `beta` in `ORPOConfig` due to trl mapping.</span></span>
|
||||
<span id="cb1-949"><a href="#cb1-949" aria-hidden="true" tabindex="-1"></a><span class="fu">orpo_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-950"><a href="#cb1-950" aria-hidden="true" tabindex="-1"></a><span class="co"># Weighting of NLL term in loss from RPO paper</span></span>
|
||||
<span id="cb1-951"><a href="#cb1-951" aria-hidden="true" tabindex="-1"></a><span class="fu">rpo_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-952"><a href="#cb1-952" aria-hidden="true" tabindex="-1"></a><span class="co"># Target reward margin for the SimPO loss</span></span>
|
||||
<span id="cb1-953"><a href="#cb1-953" aria-hidden="true" tabindex="-1"></a><span class="fu">simpo_gamma</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-954"><a href="#cb1-954" aria-hidden="true" tabindex="-1"></a><span class="co"># Weight of the BC regularizer</span></span>
|
||||
<span id="cb1-955"><a href="#cb1-955" aria-hidden="true" tabindex="-1"></a><span class="fu">cpo_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-956"><a href="#cb1-956" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-957"><a href="#cb1-957" aria-hidden="true" tabindex="-1"></a><span class="co"># Factor for desirable loss term in KTO loss</span></span>
|
||||
<span id="cb1-958"><a href="#cb1-958" aria-hidden="true" tabindex="-1"></a><span class="fu">kto_desirable_weight</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-959"><a href="#cb1-959" aria-hidden="true" tabindex="-1"></a><span class="co"># Factor for undesirable loss term in KTO loss</span></span>
|
||||
<span id="cb1-960"><a href="#cb1-960" aria-hidden="true" tabindex="-1"></a><span class="fu">kto_undesirable_weight</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-961"><a href="#cb1-961" aria-hidden="true" tabindex="-1"></a><span class="co"># The beta parameter for the RL training</span></span>
|
||||
<span id="cb1-962"><a href="#cb1-962" aria-hidden="true" tabindex="-1"></a><span class="fu">rl_beta</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-963"><a href="#cb1-963" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-964"><a href="#cb1-964" aria-hidden="true" tabindex="-1"></a><span class="co"># Defines the max memory usage per gpu on the system. Passed through to transformers</span></span>
|
||||
<span id="cb1-965"><a href="#cb1-965" aria-hidden="true" tabindex="-1"></a><span class="co"># when loading the model.</span></span>
|
||||
<span id="cb1-966"><a href="#cb1-966" aria-hidden="true" tabindex="-1"></a><span class="fu">max_memory</span><span class="kw">:</span><span class="at"> dict[int | Literal['cpu', 'disk'], int | str] | None</span></span>
|
||||
<span id="cb1-967"><a href="#cb1-967" aria-hidden="true" tabindex="-1"></a><span class="co"># Limit the memory for all available GPUs to this amount (if an integer, expressed in</span></span>
|
||||
<span id="cb1-968"><a href="#cb1-968" aria-hidden="true" tabindex="-1"></a><span class="co"># gigabytes); default: unset</span></span>
|
||||
<span id="cb1-969"><a href="#cb1-969" aria-hidden="true" tabindex="-1"></a><span class="fu">gpu_memory_limit</span><span class="kw">:</span><span class="at"> int | str | None</span></span>
|
||||
<span id="cb1-970"><a href="#cb1-970" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use low_cpu_mem_usage</span></span>
|
||||
<span id="cb1-971"><a href="#cb1-971" aria-hidden="true" tabindex="-1"></a><span class="fu">low_cpu_mem_usage</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-972"><a href="#cb1-972" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-973"><a href="#cb1-973" aria-hidden="true" tabindex="-1"></a><span class="co"># The name of the chat template to use for training, following values are supported:</span></span>
|
||||
<span id="cb1-974"><a href="#cb1-974" aria-hidden="true" tabindex="-1"></a><span class="co"># tokenizer_default: Uses the chat template that is available in the</span></span>
|
||||
<span id="cb1-975"><a href="#cb1-975" aria-hidden="true" tabindex="-1"></a><span class="co"># tokenizer_config.json. If the chat template is not available in the tokenizer, it will</span></span>
|
||||
<span id="cb1-976"><a href="#cb1-976" aria-hidden="true" tabindex="-1"></a><span class="co"># raise an error. This is the default value.</span></span>
|
||||
<span id="cb1-977"><a href="#cb1-977" aria-hidden="true" tabindex="-1"></a><span class="co"># alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates</span></span>
|
||||
<span id="cb1-978"><a href="#cb1-978" aria-hidden="true" tabindex="-1"></a><span class="co"># are available in the axolotl codebase at src/axolotl/utils/chat_templates.py.</span></span>
|
||||
<span id="cb1-979"><a href="#cb1-979" aria-hidden="true" tabindex="-1"></a><span class="co"># tokenizer_default_fallback_*: where * is the name of the chat template to fallback to.</span></span>
|
||||
<span id="cb1-980"><a href="#cb1-980" aria-hidden="true" tabindex="-1"></a><span class="co"># E.g. tokenizer_default_fallback_chatml. This is useful when the chat template is not</span></span>
|
||||
<span id="cb1-981"><a href="#cb1-981" aria-hidden="true" tabindex="-1"></a><span class="co"># available in the tokenizer. jinja: Uses a custom jinja template for the chat template.</span></span>
|
||||
<span id="cb1-982"><a href="#cb1-982" aria-hidden="true" tabindex="-1"></a><span class="co"># The custom jinja template should be provided in the chat_template_jinja field. The</span></span>
|
||||
<span id="cb1-983"><a href="#cb1-983" aria-hidden="true" tabindex="-1"></a><span class="co"># selected chat template will be saved to the tokenizer_config.json for easier</span></span>
|
||||
<span id="cb1-984"><a href="#cb1-984" aria-hidden="true" tabindex="-1"></a><span class="co"># inferencing</span></span>
|
||||
<span id="cb1-985"><a href="#cb1-985" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> ChatTemplate | Annotated[str, StringConstraints(pattern='^tokenizer_default_fallback_')] | None</span></span>
|
||||
<span id="cb1-986"><a href="#cb1-986" aria-hidden="true" tabindex="-1"></a><span class="co"># Custom jinja template or path to jinja file for chat template. This will be only used</span></span>
|
||||
<span id="cb1-987"><a href="#cb1-987" aria-hidden="true" tabindex="-1"></a><span class="co"># if chat_template is set to `jinja` or `null` (in which case chat_template is</span></span>
|
||||
<span id="cb1-988"><a href="#cb1-988" aria-hidden="true" tabindex="-1"></a><span class="co"># automatically set to `jinja`). Default is null.</span></span>
|
||||
<span id="cb1-989"><a href="#cb1-989" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template_jinja</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-990"><a href="#cb1-990" aria-hidden="true" tabindex="-1"></a><span class="co"># Additional kwargs to pass to the chat template. This is useful for customizing the</span></span>
|
||||
<span id="cb1-991"><a href="#cb1-991" aria-hidden="true" tabindex="-1"></a><span class="co"># chat template. For example, you can pass `thinking=False` to add a generation prompt</span></span>
|
||||
<span id="cb1-992"><a href="#cb1-992" aria-hidden="true" tabindex="-1"></a><span class="co"># to the chat template.</span></span>
|
||||
<span id="cb1-993"><a href="#cb1-993" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-994"><a href="#cb1-994" aria-hidden="true" tabindex="-1"></a><span class="co"># Custom EOT (End-of-Turn) tokens to mask/unmask during training. These tokens mark the</span></span>
|
||||
<span id="cb1-995"><a href="#cb1-995" aria-hidden="true" tabindex="-1"></a><span class="co"># boundaries between conversation turns. For example: ['/INST', '</s>',</span></span>
|
||||
<span id="cb1-996"><a href="#cb1-996" aria-hidden="true" tabindex="-1"></a><span class="co"># '[/SYSTEM_PROMPT]']. If not specified, defaults to just the model's eos_token. This is</span></span>
|
||||
<span id="cb1-997"><a href="#cb1-997" aria-hidden="true" tabindex="-1"></a><span class="co"># useful for templates that use multiple delimiter tokens.</span></span>
|
||||
<span id="cb1-998"><a href="#cb1-998" aria-hidden="true" tabindex="-1"></a><span class="fu">eot_tokens</span><span class="kw">:</span><span class="at"> list[str] | None</span></span>
|
||||
<span id="cb1-999"><a href="#cb1-999" aria-hidden="true" tabindex="-1"></a><span class="co"># Changes the default system message. Currently only supports chatml.</span></span>
|
||||
<span id="cb1-1000"><a href="#cb1-1000" aria-hidden="true" tabindex="-1"></a><span class="fu">default_system_message</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1001"><a href="#cb1-1001" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1002"><a href="#cb1-1002" aria-hidden="true" tabindex="-1"></a><span class="fu">fix_untrained_tokens</span><span class="kw">:</span><span class="at"> int | list[int] | None</span></span>
|
||||
<span id="cb1-942"><a href="#cb1-942" aria-hidden="true" tabindex="-1"></a><span class="co"># bool of whether to report tokens per second during training by measuring throughput of</span></span>
|
||||
<span id="cb1-943"><a href="#cb1-943" aria-hidden="true" tabindex="-1"></a><span class="co"># non-padding tokens.</span></span>
|
||||
<span id="cb1-944"><a href="#cb1-944" aria-hidden="true" tabindex="-1"></a><span class="fu">include_tkps</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-945"><a href="#cb1-945" aria-hidden="true" tabindex="-1"></a><span class="co"># NEFT https://arxiv.org/abs/2310.05914, set this to a number (paper default is 5) to</span></span>
|
||||
<span id="cb1-946"><a href="#cb1-946" aria-hidden="true" tabindex="-1"></a><span class="co"># add noise to embeddings. Currently only supported on Llama and Mistral</span></span>
|
||||
<span id="cb1-947"><a href="#cb1-947" aria-hidden="true" tabindex="-1"></a><span class="fu">neftune_noise_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-948"><a href="#cb1-948" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-949"><a href="#cb1-949" aria-hidden="true" tabindex="-1"></a><span class="co"># Parameter controlling the relative ratio loss weight in the ORPO loss. Passed to</span></span>
|
||||
<span id="cb1-950"><a href="#cb1-950" aria-hidden="true" tabindex="-1"></a><span class="co"># `beta` in `ORPOConfig` due to trl mapping.</span></span>
|
||||
<span id="cb1-951"><a href="#cb1-951" aria-hidden="true" tabindex="-1"></a><span class="fu">orpo_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-952"><a href="#cb1-952" aria-hidden="true" tabindex="-1"></a><span class="co"># Weighting of NLL term in loss from RPO paper</span></span>
|
||||
<span id="cb1-953"><a href="#cb1-953" aria-hidden="true" tabindex="-1"></a><span class="fu">rpo_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-954"><a href="#cb1-954" aria-hidden="true" tabindex="-1"></a><span class="co"># Target reward margin for the SimPO loss</span></span>
|
||||
<span id="cb1-955"><a href="#cb1-955" aria-hidden="true" tabindex="-1"></a><span class="fu">simpo_gamma</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-956"><a href="#cb1-956" aria-hidden="true" tabindex="-1"></a><span class="co"># Weight of the BC regularizer</span></span>
|
||||
<span id="cb1-957"><a href="#cb1-957" aria-hidden="true" tabindex="-1"></a><span class="fu">cpo_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-958"><a href="#cb1-958" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-959"><a href="#cb1-959" aria-hidden="true" tabindex="-1"></a><span class="co"># Factor for desirable loss term in KTO loss</span></span>
|
||||
<span id="cb1-960"><a href="#cb1-960" aria-hidden="true" tabindex="-1"></a><span class="fu">kto_desirable_weight</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-961"><a href="#cb1-961" aria-hidden="true" tabindex="-1"></a><span class="co"># Factor for undesirable loss term in KTO loss</span></span>
|
||||
<span id="cb1-962"><a href="#cb1-962" aria-hidden="true" tabindex="-1"></a><span class="fu">kto_undesirable_weight</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-963"><a href="#cb1-963" aria-hidden="true" tabindex="-1"></a><span class="co"># The beta parameter for the RL training</span></span>
|
||||
<span id="cb1-964"><a href="#cb1-964" aria-hidden="true" tabindex="-1"></a><span class="fu">rl_beta</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-965"><a href="#cb1-965" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-966"><a href="#cb1-966" aria-hidden="true" tabindex="-1"></a><span class="co"># Defines the max memory usage per gpu on the system. Passed through to transformers</span></span>
|
||||
<span id="cb1-967"><a href="#cb1-967" aria-hidden="true" tabindex="-1"></a><span class="co"># when loading the model.</span></span>
|
||||
<span id="cb1-968"><a href="#cb1-968" aria-hidden="true" tabindex="-1"></a><span class="fu">max_memory</span><span class="kw">:</span><span class="at"> dict[int | Literal['cpu', 'disk'], int | str] | None</span></span>
|
||||
<span id="cb1-969"><a href="#cb1-969" aria-hidden="true" tabindex="-1"></a><span class="co"># Limit the memory for all available GPUs to this amount (if an integer, expressed in</span></span>
|
||||
<span id="cb1-970"><a href="#cb1-970" aria-hidden="true" tabindex="-1"></a><span class="co"># gigabytes); default: unset</span></span>
|
||||
<span id="cb1-971"><a href="#cb1-971" aria-hidden="true" tabindex="-1"></a><span class="fu">gpu_memory_limit</span><span class="kw">:</span><span class="at"> int | str | None</span></span>
|
||||
<span id="cb1-972"><a href="#cb1-972" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use low_cpu_mem_usage</span></span>
|
||||
<span id="cb1-973"><a href="#cb1-973" aria-hidden="true" tabindex="-1"></a><span class="fu">low_cpu_mem_usage</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-974"><a href="#cb1-974" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-975"><a href="#cb1-975" aria-hidden="true" tabindex="-1"></a><span class="co"># The name of the chat template to use for training, following values are supported:</span></span>
|
||||
<span id="cb1-976"><a href="#cb1-976" aria-hidden="true" tabindex="-1"></a><span class="co"># tokenizer_default: Uses the chat template that is available in the</span></span>
|
||||
<span id="cb1-977"><a href="#cb1-977" aria-hidden="true" tabindex="-1"></a><span class="co"># tokenizer_config.json. If the chat template is not available in the tokenizer, it will</span></span>
|
||||
<span id="cb1-978"><a href="#cb1-978" aria-hidden="true" tabindex="-1"></a><span class="co"># raise an error. This is the default value.</span></span>
|
||||
<span id="cb1-979"><a href="#cb1-979" aria-hidden="true" tabindex="-1"></a><span class="co"># alpaca/inst/chatml/gemma/cohere/llama3/phi_3/deepseek_v2/jamba: These chat templates</span></span>
|
||||
<span id="cb1-980"><a href="#cb1-980" aria-hidden="true" tabindex="-1"></a><span class="co"># are available in the axolotl codebase at src/axolotl/utils/chat_templates.py.</span></span>
|
||||
<span id="cb1-981"><a href="#cb1-981" aria-hidden="true" tabindex="-1"></a><span class="co"># tokenizer_default_fallback_*: where * is the name of the chat template to fallback to.</span></span>
|
||||
<span id="cb1-982"><a href="#cb1-982" aria-hidden="true" tabindex="-1"></a><span class="co"># E.g. tokenizer_default_fallback_chatml. This is useful when the chat template is not</span></span>
|
||||
<span id="cb1-983"><a href="#cb1-983" aria-hidden="true" tabindex="-1"></a><span class="co"># available in the tokenizer. jinja: Uses a custom jinja template for the chat template.</span></span>
|
||||
<span id="cb1-984"><a href="#cb1-984" aria-hidden="true" tabindex="-1"></a><span class="co"># The custom jinja template should be provided in the chat_template_jinja field. The</span></span>
|
||||
<span id="cb1-985"><a href="#cb1-985" aria-hidden="true" tabindex="-1"></a><span class="co"># selected chat template will be saved to the tokenizer_config.json for easier</span></span>
|
||||
<span id="cb1-986"><a href="#cb1-986" aria-hidden="true" tabindex="-1"></a><span class="co"># inferencing</span></span>
|
||||
<span id="cb1-987"><a href="#cb1-987" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template</span><span class="kw">:</span><span class="at"> ChatTemplate | Annotated[str, StringConstraints(pattern='^tokenizer_default_fallback_')] | None</span></span>
|
||||
<span id="cb1-988"><a href="#cb1-988" aria-hidden="true" tabindex="-1"></a><span class="co"># Custom jinja template or path to jinja file for chat template. This will be only used</span></span>
|
||||
<span id="cb1-989"><a href="#cb1-989" aria-hidden="true" tabindex="-1"></a><span class="co"># if chat_template is set to `jinja` or `null` (in which case chat_template is</span></span>
|
||||
<span id="cb1-990"><a href="#cb1-990" aria-hidden="true" tabindex="-1"></a><span class="co"># automatically set to `jinja`). Default is null.</span></span>
|
||||
<span id="cb1-991"><a href="#cb1-991" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template_jinja</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-992"><a href="#cb1-992" aria-hidden="true" tabindex="-1"></a><span class="co"># Additional kwargs to pass to the chat template. This is useful for customizing the</span></span>
|
||||
<span id="cb1-993"><a href="#cb1-993" aria-hidden="true" tabindex="-1"></a><span class="co"># chat template. For example, you can pass `thinking=False` to add a generation prompt</span></span>
|
||||
<span id="cb1-994"><a href="#cb1-994" aria-hidden="true" tabindex="-1"></a><span class="co"># to the chat template.</span></span>
|
||||
<span id="cb1-995"><a href="#cb1-995" aria-hidden="true" tabindex="-1"></a><span class="fu">chat_template_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-996"><a href="#cb1-996" aria-hidden="true" tabindex="-1"></a><span class="co"># Custom EOT (End-of-Turn) tokens to mask/unmask during training. These tokens mark the</span></span>
|
||||
<span id="cb1-997"><a href="#cb1-997" aria-hidden="true" tabindex="-1"></a><span class="co"># boundaries between conversation turns. For example: ['/INST', '</s>',</span></span>
|
||||
<span id="cb1-998"><a href="#cb1-998" aria-hidden="true" tabindex="-1"></a><span class="co"># '[/SYSTEM_PROMPT]']. If not specified, defaults to just the model's eos_token. This is</span></span>
|
||||
<span id="cb1-999"><a href="#cb1-999" aria-hidden="true" tabindex="-1"></a><span class="co"># useful for templates that use multiple delimiter tokens.</span></span>
|
||||
<span id="cb1-1000"><a href="#cb1-1000" aria-hidden="true" tabindex="-1"></a><span class="fu">eot_tokens</span><span class="kw">:</span><span class="at"> list[str] | None</span></span>
|
||||
<span id="cb1-1001"><a href="#cb1-1001" aria-hidden="true" tabindex="-1"></a><span class="co"># Changes the default system message. Currently only supports chatml.</span></span>
|
||||
<span id="cb1-1002"><a href="#cb1-1002" aria-hidden="true" tabindex="-1"></a><span class="fu">default_system_message</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1003"><a href="#cb1-1003" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1004"><a href="#cb1-1004" aria-hidden="true" tabindex="-1"></a><span class="fu">is_preprocess</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1005"><a href="#cb1-1005" aria-hidden="true" tabindex="-1"></a><span class="fu">preprocess_iterable</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1006"><a href="#cb1-1006" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1007"><a href="#cb1-1007" aria-hidden="true" tabindex="-1"></a><span class="co"># Total number of tokens - internal use</span></span>
|
||||
<span id="cb1-1008"><a href="#cb1-1008" aria-hidden="true" tabindex="-1"></a><span class="fu">total_num_tokens</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1009"><a href="#cb1-1009" aria-hidden="true" tabindex="-1"></a><span class="fu">total_supervised_tokens</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1010"><a href="#cb1-1010" aria-hidden="true" tabindex="-1"></a><span class="co"># You can set these packing optimizations AFTER starting a training at least once. The</span></span>
|
||||
<span id="cb1-1011"><a href="#cb1-1011" aria-hidden="true" tabindex="-1"></a><span class="co"># trainer will provide recommended values for these values.</span></span>
|
||||
<span id="cb1-1012"><a href="#cb1-1012" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing_eff_est</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1013"><a href="#cb1-1013" aria-hidden="true" tabindex="-1"></a><span class="fu">axolotl_config_path</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1014"><a href="#cb1-1014" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1015"><a href="#cb1-1015" aria-hidden="true" tabindex="-1"></a><span class="co"># Internal use only - Used to identify which the model is based on</span></span>
|
||||
<span id="cb1-1016"><a href="#cb1-1016" aria-hidden="true" tabindex="-1"></a><span class="fu">is_falcon_derived_model</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1004"><a href="#cb1-1004" aria-hidden="true" tabindex="-1"></a><span class="fu">fix_untrained_tokens</span><span class="kw">:</span><span class="at"> int | list[int] | None</span></span>
|
||||
<span id="cb1-1005"><a href="#cb1-1005" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1006"><a href="#cb1-1006" aria-hidden="true" tabindex="-1"></a><span class="fu">is_preprocess</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1007"><a href="#cb1-1007" aria-hidden="true" tabindex="-1"></a><span class="fu">preprocess_iterable</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1008"><a href="#cb1-1008" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1009"><a href="#cb1-1009" aria-hidden="true" tabindex="-1"></a><span class="co"># Total number of tokens - internal use</span></span>
|
||||
<span id="cb1-1010"><a href="#cb1-1010" aria-hidden="true" tabindex="-1"></a><span class="fu">total_num_tokens</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1011"><a href="#cb1-1011" aria-hidden="true" tabindex="-1"></a><span class="fu">total_supervised_tokens</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1012"><a href="#cb1-1012" aria-hidden="true" tabindex="-1"></a><span class="co"># You can set these packing optimizations AFTER starting a training at least once. The</span></span>
|
||||
<span id="cb1-1013"><a href="#cb1-1013" aria-hidden="true" tabindex="-1"></a><span class="co"># trainer will provide recommended values for these values.</span></span>
|
||||
<span id="cb1-1014"><a href="#cb1-1014" aria-hidden="true" tabindex="-1"></a><span class="fu">sample_packing_eff_est</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1015"><a href="#cb1-1015" aria-hidden="true" tabindex="-1"></a><span class="fu">axolotl_config_path</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1016"><a href="#cb1-1016" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1017"><a href="#cb1-1017" aria-hidden="true" tabindex="-1"></a><span class="co"># Internal use only - Used to identify which the model is based on</span></span>
|
||||
<span id="cb1-1018"><a href="#cb1-1018" aria-hidden="true" tabindex="-1"></a><span class="fu">is_llama_derived_model</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1019"><a href="#cb1-1019" aria-hidden="true" tabindex="-1"></a><span class="co"># Internal use only - Used to identify which the model is based on. Please note that if</span></span>
|
||||
<span id="cb1-1020"><a href="#cb1-1020" aria-hidden="true" tabindex="-1"></a><span class="co"># you set this to true, `padding_side` will be set to 'left' by default</span></span>
|
||||
<span id="cb1-1021"><a href="#cb1-1021" aria-hidden="true" tabindex="-1"></a><span class="fu">is_mistral_derived_model</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1022"><a href="#cb1-1022" aria-hidden="true" tabindex="-1"></a><span class="co"># Internal use only - Used to identify which the model is based on</span></span>
|
||||
<span id="cb1-1023"><a href="#cb1-1023" aria-hidden="true" tabindex="-1"></a><span class="fu">is_qwen_derived_model</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1024"><a href="#cb1-1024" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1025"><a href="#cb1-1025" aria-hidden="true" tabindex="-1"></a><span class="co"># Add plugins to extend the pipeline. See `src/axolotl/integrations` for the available</span></span>
|
||||
<span id="cb1-1026"><a href="#cb1-1026" aria-hidden="true" tabindex="-1"></a><span class="co"># plugins or doc below for more details.</span></span>
|
||||
<span id="cb1-1027"><a href="#cb1-1027" aria-hidden="true" tabindex="-1"></a><span class="co"># https://docs.axolotl.ai/docs/custom_integrations.html</span></span>
|
||||
<span id="cb1-1028"><a href="#cb1-1028" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span><span class="at"> list[str] | None</span></span>
|
||||
<span id="cb1-1029"><a href="#cb1-1029" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1030"><a href="#cb1-1030" aria-hidden="true" tabindex="-1"></a><span class="co"># This is the huggingface model that contains *.pt, *.safetensors, or *.bin files. This</span></span>
|
||||
<span id="cb1-1031"><a href="#cb1-1031" aria-hidden="true" tabindex="-1"></a><span class="co"># can also be a relative path to a model on disk</span></span>
|
||||
<span id="cb1-1032"><a href="#cb1-1032" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> str (required)</span></span>
|
||||
<span id="cb1-1033"><a href="#cb1-1033" aria-hidden="true" tabindex="-1"></a><span class="co"># If the base_model repo on hf hub doesn't include configuration .json files, You can</span></span>
|
||||
<span id="cb1-1034"><a href="#cb1-1034" aria-hidden="true" tabindex="-1"></a><span class="co"># set that here, or leave this empty to default to base_model</span></span>
|
||||
<span id="cb1-1035"><a href="#cb1-1035" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model_config</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1036"><a href="#cb1-1036" aria-hidden="true" tabindex="-1"></a><span class="fu">cls_model_config</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1037"><a href="#cb1-1037" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional tokenizer configuration path in case you want to use a different tokenizer</span></span>
|
||||
<span id="cb1-1038"><a href="#cb1-1038" aria-hidden="true" tabindex="-1"></a><span class="co"># than the one defined in the base model</span></span>
|
||||
<span id="cb1-1039"><a href="#cb1-1039" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_config</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1040"><a href="#cb1-1040" aria-hidden="true" tabindex="-1"></a><span class="co"># use_fast option for tokenizer loading from_pretrained, default to True</span></span>
|
||||
<span id="cb1-1041"><a href="#cb1-1041" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_use_fast</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1042"><a href="#cb1-1042" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use the legacy tokenizer setting, defaults to True</span></span>
|
||||
<span id="cb1-1043"><a href="#cb1-1043" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_legacy</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1044"><a href="#cb1-1044" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use mistral-common tokenizer. If set to True, it will use the mistral-</span></span>
|
||||
<span id="cb1-1045"><a href="#cb1-1045" aria-hidden="true" tabindex="-1"></a><span class="co"># common tokenizer.</span></span>
|
||||
<span id="cb1-1046"><a href="#cb1-1046" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_use_mistral_common</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1047"><a href="#cb1-1047" aria-hidden="true" tabindex="-1"></a><span class="co"># Corresponding tokenizer for the model AutoTokenizer is a good choice</span></span>
|
||||
<span id="cb1-1048"><a href="#cb1-1048" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_type</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1049"><a href="#cb1-1049" aria-hidden="true" tabindex="-1"></a><span class="co"># transformers processor class</span></span>
|
||||
<span id="cb1-1050"><a href="#cb1-1050" aria-hidden="true" tabindex="-1"></a><span class="fu">processor_type</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1051"><a href="#cb1-1051" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to save jinja files for tokenizer, transformers default is True</span></span>
|
||||
<span id="cb1-1052"><a href="#cb1-1052" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_save_jinja_files</span><span class="kw">:</span><span class="at"> bool | None = True</span></span>
|
||||
<span id="cb1-1053"><a href="#cb1-1053" aria-hidden="true" tabindex="-1"></a><span class="co"># Trust remote code for untrusted source</span></span>
|
||||
<span id="cb1-1054"><a href="#cb1-1054" aria-hidden="true" tabindex="-1"></a><span class="fu">trust_remote_code</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1055"><a href="#cb1-1055" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1056"><a href="#cb1-1056" aria-hidden="true" tabindex="-1"></a><span class="co"># Don't move the model to the device before sharding. Set to `false` to revert to legacy</span></span>
|
||||
<span id="cb1-1057"><a href="#cb1-1057" aria-hidden="true" tabindex="-1"></a><span class="co"># behavior.</span></span>
|
||||
<span id="cb1-1058"><a href="#cb1-1058" aria-hidden="true" tabindex="-1"></a><span class="fu">experimental_skip_move_to_device</span><span class="kw">:</span><span class="at"> bool | None = True</span></span>
|
||||
<span id="cb1-1059"><a href="#cb1-1059" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1060"><a href="#cb1-1060" aria-hidden="true" tabindex="-1"></a><span class="co"># Use custom kernels, e.g. MegaBlocks.</span></span>
|
||||
<span id="cb1-1061"><a href="#cb1-1061" aria-hidden="true" tabindex="-1"></a><span class="fu">use_kernels</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1062"><a href="#cb1-1062" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1063"><a href="#cb1-1063" aria-hidden="true" tabindex="-1"></a><span class="co"># Model loading quantization config</span></span>
|
||||
<span id="cb1-1064"><a href="#cb1-1064" aria-hidden="true" tabindex="-1"></a><span class="fu">model_quantization_config</span><span class="kw">:</span><span class="at"> Literal['Mxfp4Config'] | None</span></span>
|
||||
<span id="cb1-1065"><a href="#cb1-1065" aria-hidden="true" tabindex="-1"></a><span class="co"># kwargs for model quantization config</span></span>
|
||||
<span id="cb1-1066"><a href="#cb1-1066" aria-hidden="true" tabindex="-1"></a><span class="fu">model_quantization_config_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1067"><a href="#cb1-1067" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1068"><a href="#cb1-1068" aria-hidden="true" tabindex="-1"></a><span class="co"># Where to save the full-finetuned model to</span></span>
|
||||
<span id="cb1-1069"><a href="#cb1-1069" aria-hidden="true" tabindex="-1"></a><span class="fu">output_dir</span><span class="kw">:</span><span class="at"> str = ./model-out</span></span>
|
||||
<span id="cb1-1070"><a href="#cb1-1070" aria-hidden="true" tabindex="-1"></a><span class="co"># push checkpoints to hub</span></span>
|
||||
<span id="cb1-1071"><a href="#cb1-1071" aria-hidden="true" tabindex="-1"></a><span class="fu">hub_model_id</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1072"><a href="#cb1-1072" aria-hidden="true" tabindex="-1"></a><span class="co"># how to push checkpoints to hub</span></span>
|
||||
<span id="cb1-1073"><a href="#cb1-1073" aria-hidden="true" tabindex="-1"></a><span class="fu">hub_strategy</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1074"><a href="#cb1-1074" aria-hidden="true" tabindex="-1"></a><span class="co"># Save model as safetensors (require safetensors package). Default True</span></span>
|
||||
<span id="cb1-1075"><a href="#cb1-1075" aria-hidden="true" tabindex="-1"></a><span class="fu">save_safetensors</span><span class="kw">:</span><span class="at"> bool | None = True</span></span>
|
||||
<span id="cb1-1076"><a href="#cb1-1076" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1077"><a href="#cb1-1077" aria-hidden="true" tabindex="-1"></a><span class="co"># This will attempt to quantize the model down to 8 bits and use adam 8 bit optimizer</span></span>
|
||||
<span id="cb1-1078"><a href="#cb1-1078" aria-hidden="true" tabindex="-1"></a><span class="fu">load_in_8bit</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1079"><a href="#cb1-1079" aria-hidden="true" tabindex="-1"></a><span class="co"># Use bitsandbytes 4 bit</span></span>
|
||||
<span id="cb1-1080"><a href="#cb1-1080" aria-hidden="true" tabindex="-1"></a><span class="fu">load_in_4bit</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1081"><a href="#cb1-1081" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1082"><a href="#cb1-1082" aria-hidden="true" tabindex="-1"></a><span class="co"># If you want to use 'lora' or 'qlora' or leave blank to train all parameters in</span></span>
|
||||
<span id="cb1-1083"><a href="#cb1-1083" aria-hidden="true" tabindex="-1"></a><span class="co"># original model</span></span>
|
||||
<span id="cb1-1084"><a href="#cb1-1084" aria-hidden="true" tabindex="-1"></a><span class="fu">adapter</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1085"><a href="#cb1-1085" aria-hidden="true" tabindex="-1"></a><span class="co"># If you already have a lora model trained that you want to load, put that here. This</span></span>
|
||||
<span id="cb1-1086"><a href="#cb1-1086" aria-hidden="true" tabindex="-1"></a><span class="co"># means after training, if you want to test the model, you should set this to the value</span></span>
|
||||
<span id="cb1-1087"><a href="#cb1-1087" aria-hidden="true" tabindex="-1"></a><span class="co"># of `output_dir`. Note that if you merge an adapter to the base model, a new</span></span>
|
||||
<span id="cb1-1088"><a href="#cb1-1088" aria-hidden="true" tabindex="-1"></a><span class="co"># subdirectory `merged` will be created under the `output_dir`.</span></span>
|
||||
<span id="cb1-1089"><a href="#cb1-1089" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_model_dir</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1090"><a href="#cb1-1090" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_r</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1091"><a href="#cb1-1091" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_alpha</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1092"><a href="#cb1-1092" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_fan_in_fan_out</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1093"><a href="#cb1-1093" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_modules</span><span class="kw">:</span><span class="at"> str | list[str] | None</span></span>
|
||||
<span id="cb1-1094"><a href="#cb1-1094" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_parameters</span><span class="kw">:</span><span class="at"> str | list[str] | None</span></span>
|
||||
<span id="cb1-1095"><a href="#cb1-1095" aria-hidden="true" tabindex="-1"></a><span class="co"># If true, will target all linear modules</span></span>
|
||||
<span id="cb1-1096"><a href="#cb1-1096" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_linear</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1097"><a href="#cb1-1097" aria-hidden="true" tabindex="-1"></a><span class="co"># If you added new tokens to the tokenizer, you may need to save some LoRA modules</span></span>
|
||||
<span id="cb1-1098"><a href="#cb1-1098" aria-hidden="true" tabindex="-1"></a><span class="co"># because they need to know the new tokens. For LLaMA and Mistral, you need to save</span></span>
|
||||
<span id="cb1-1099"><a href="#cb1-1099" aria-hidden="true" tabindex="-1"></a><span class="co"># `embed_tokens` and `lm_head`. It may vary for other models. `embed_tokens` converts</span></span>
|
||||
<span id="cb1-1100"><a href="#cb1-1100" aria-hidden="true" tabindex="-1"></a><span class="co"># tokens to embeddings, and `lm_head` converts embeddings to token probabilities.</span></span>
|
||||
<span id="cb1-1101"><a href="#cb1-1101" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_modules_to_save</span><span class="kw">:</span><span class="at"> list[str] | None</span></span>
|
||||
<span id="cb1-1102"><a href="#cb1-1102" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_dropout</span><span class="kw">:</span><span class="at"> float | None = 0.0</span></span>
|
||||
<span id="cb1-1103"><a href="#cb1-1103" aria-hidden="true" tabindex="-1"></a><span class="co"># The layer indices to transform, otherwise, apply to all layers</span></span>
|
||||
<span id="cb1-1104"><a href="#cb1-1104" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_layers_to_transform</span><span class="kw">:</span><span class="at"> list[int] | None</span></span>
|
||||
<span id="cb1-1105"><a href="#cb1-1105" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_layers_pattern</span><span class="kw">:</span><span class="at"> list[str] | None</span></span>
|
||||
<span id="cb1-1106"><a href="#cb1-1106" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1107"><a href="#cb1-1107" aria-hidden="true" tabindex="-1"></a><span class="fu">peft</span><span class="kw">:</span><span class="at"> PeftConfig | None</span></span>
|
||||
<span id="cb1-1108"><a href="#cb1-1108" aria-hidden="true" tabindex="-1"></a><span class="co"> # For PeftConfig:</span></span>
|
||||
<span id="cb1-1109"><a href="#cb1-1109" aria-hidden="true" tabindex="-1"></a><span class="co"> # Configuration options for loftq initialization for LoRA</span></span>
|
||||
<span id="cb1-1110"><a href="#cb1-1110" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">loftq_config</span><span class="kw">:</span><span class="at"> LoftQConfig | None</span></span>
|
||||
<span id="cb1-1111"><a href="#cb1-1111" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LoftQConfig:</span></span>
|
||||
<span id="cb1-1112"><a href="#cb1-1112" aria-hidden="true" tabindex="-1"></a><span class="co"> # typically 4 bits</span></span>
|
||||
<span id="cb1-1113"><a href="#cb1-1113" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">loftq_bits</span><span class="kw">:</span><span class="at"> int = 4</span></span>
|
||||
<span id="cb1-1114"><a href="#cb1-1114" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1115"><a href="#cb1-1115" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use DoRA.</span></span>
|
||||
<span id="cb1-1116"><a href="#cb1-1116" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_use_dora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1117"><a href="#cb1-1117" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use RSLoRA.</span></span>
|
||||
<span id="cb1-1118"><a href="#cb1-1118" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_use_rslora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1119"><a href="#cb1-1119" aria-hidden="true" tabindex="-1"></a><span class="co"># List of layer indices to replicate.</span></span>
|
||||
<span id="cb1-1120"><a href="#cb1-1120" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_layer_replication</span><span class="kw">:</span><span class="at"> list[tuple[int, int]] | None</span></span>
|
||||
<span id="cb1-1121"><a href="#cb1-1121" aria-hidden="true" tabindex="-1"></a><span class="co"># How to initialize LoRA weights. Default to True which is MS original implementation.</span></span>
|
||||
<span id="cb1-1122"><a href="#cb1-1122" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_init_lora_weights</span><span class="kw">:</span><span class="at"> bool | str | None</span></span>
|
||||
<span id="cb1-1123"><a href="#cb1-1123" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1124"><a href="#cb1-1124" aria-hidden="true" tabindex="-1"></a><span class="co"># load qlora model in sharded format for FSDP using answer.ai technique.</span></span>
|
||||
<span id="cb1-1125"><a href="#cb1-1125" aria-hidden="true" tabindex="-1"></a><span class="fu">qlora_sharded_model_loading</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1126"><a href="#cb1-1126" aria-hidden="true" tabindex="-1"></a><span class="co"># Do the LoRA/PEFT loading on CPU -- this is required if the base model is so large it</span></span>
|
||||
<span id="cb1-1127"><a href="#cb1-1127" aria-hidden="true" tabindex="-1"></a><span class="co"># takes up most or all of the available GPU VRAM, e.g. during a model and LoRA merge</span></span>
|
||||
<span id="cb1-1128"><a href="#cb1-1128" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_on_cpu</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1129"><a href="#cb1-1129" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether you are training a 4-bit GPTQ quantized model</span></span>
|
||||
<span id="cb1-1130"><a href="#cb1-1130" aria-hidden="true" tabindex="-1"></a><span class="fu">gptq</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1131"><a href="#cb1-1131" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the bnb 4bit quantization configuration</span></span>
|
||||
<span id="cb1-1132"><a href="#cb1-1132" aria-hidden="true" tabindex="-1"></a><span class="fu">bnb_config_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1133"><a href="#cb1-1133" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1134"><a href="#cb1-1134" aria-hidden="true" tabindex="-1"></a><span class="co"># loraplus learning rate ratio lr_B / lr_A. Recommended value is 2^4.</span></span>
|
||||
<span id="cb1-1135"><a href="#cb1-1135" aria-hidden="true" tabindex="-1"></a><span class="fu">loraplus_lr_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1136"><a href="#cb1-1136" aria-hidden="true" tabindex="-1"></a><span class="co"># loraplus learning rate for lora embedding layers. Default value is 1e-6.</span></span>
|
||||
<span id="cb1-1137"><a href="#cb1-1137" aria-hidden="true" tabindex="-1"></a><span class="fu">loraplus_lr_embedding</span><span class="kw">:</span><span class="at"> float | None = 1e-06</span></span>
|
||||
<span id="cb1-1138"><a href="#cb1-1138" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1139"><a href="#cb1-1139" aria-hidden="true" tabindex="-1"></a><span class="fu">merge_lora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1018"><a href="#cb1-1018" aria-hidden="true" tabindex="-1"></a><span class="fu">is_falcon_derived_model</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1019"><a href="#cb1-1019" aria-hidden="true" tabindex="-1"></a><span class="co"># Internal use only - Used to identify which the model is based on</span></span>
|
||||
<span id="cb1-1020"><a href="#cb1-1020" aria-hidden="true" tabindex="-1"></a><span class="fu">is_llama_derived_model</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1021"><a href="#cb1-1021" aria-hidden="true" tabindex="-1"></a><span class="co"># Internal use only - Used to identify which the model is based on. Please note that if</span></span>
|
||||
<span id="cb1-1022"><a href="#cb1-1022" aria-hidden="true" tabindex="-1"></a><span class="co"># you set this to true, `padding_side` will be set to 'left' by default</span></span>
|
||||
<span id="cb1-1023"><a href="#cb1-1023" aria-hidden="true" tabindex="-1"></a><span class="fu">is_mistral_derived_model</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1024"><a href="#cb1-1024" aria-hidden="true" tabindex="-1"></a><span class="co"># Internal use only - Used to identify which the model is based on</span></span>
|
||||
<span id="cb1-1025"><a href="#cb1-1025" aria-hidden="true" tabindex="-1"></a><span class="fu">is_qwen_derived_model</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1026"><a href="#cb1-1026" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1027"><a href="#cb1-1027" aria-hidden="true" tabindex="-1"></a><span class="co"># Add plugins to extend the pipeline. See `src/axolotl/integrations` for the available</span></span>
|
||||
<span id="cb1-1028"><a href="#cb1-1028" aria-hidden="true" tabindex="-1"></a><span class="co"># plugins or doc below for more details.</span></span>
|
||||
<span id="cb1-1029"><a href="#cb1-1029" aria-hidden="true" tabindex="-1"></a><span class="co"># https://docs.axolotl.ai/docs/custom_integrations.html</span></span>
|
||||
<span id="cb1-1030"><a href="#cb1-1030" aria-hidden="true" tabindex="-1"></a><span class="fu">plugins</span><span class="kw">:</span><span class="at"> list[str] | None</span></span>
|
||||
<span id="cb1-1031"><a href="#cb1-1031" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1032"><a href="#cb1-1032" aria-hidden="true" tabindex="-1"></a><span class="co"># This is the huggingface model that contains *.pt, *.safetensors, or *.bin files. This</span></span>
|
||||
<span id="cb1-1033"><a href="#cb1-1033" aria-hidden="true" tabindex="-1"></a><span class="co"># can also be a relative path to a model on disk</span></span>
|
||||
<span id="cb1-1034"><a href="#cb1-1034" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model</span><span class="kw">:</span><span class="at"> str (required)</span></span>
|
||||
<span id="cb1-1035"><a href="#cb1-1035" aria-hidden="true" tabindex="-1"></a><span class="co"># If the base_model repo on hf hub doesn't include configuration .json files, You can</span></span>
|
||||
<span id="cb1-1036"><a href="#cb1-1036" aria-hidden="true" tabindex="-1"></a><span class="co"># set that here, or leave this empty to default to base_model</span></span>
|
||||
<span id="cb1-1037"><a href="#cb1-1037" aria-hidden="true" tabindex="-1"></a><span class="fu">base_model_config</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1038"><a href="#cb1-1038" aria-hidden="true" tabindex="-1"></a><span class="fu">cls_model_config</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1039"><a href="#cb1-1039" aria-hidden="true" tabindex="-1"></a><span class="co"># Optional tokenizer configuration path in case you want to use a different tokenizer</span></span>
|
||||
<span id="cb1-1040"><a href="#cb1-1040" aria-hidden="true" tabindex="-1"></a><span class="co"># than the one defined in the base model</span></span>
|
||||
<span id="cb1-1041"><a href="#cb1-1041" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_config</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1042"><a href="#cb1-1042" aria-hidden="true" tabindex="-1"></a><span class="co"># use_fast option for tokenizer loading from_pretrained, default to True</span></span>
|
||||
<span id="cb1-1043"><a href="#cb1-1043" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_use_fast</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1044"><a href="#cb1-1044" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use the legacy tokenizer setting, defaults to True</span></span>
|
||||
<span id="cb1-1045"><a href="#cb1-1045" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_legacy</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1046"><a href="#cb1-1046" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use mistral-common tokenizer. If set to True, it will use the mistral-</span></span>
|
||||
<span id="cb1-1047"><a href="#cb1-1047" aria-hidden="true" tabindex="-1"></a><span class="co"># common tokenizer.</span></span>
|
||||
<span id="cb1-1048"><a href="#cb1-1048" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_use_mistral_common</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1049"><a href="#cb1-1049" aria-hidden="true" tabindex="-1"></a><span class="co"># Corresponding tokenizer for the model AutoTokenizer is a good choice</span></span>
|
||||
<span id="cb1-1050"><a href="#cb1-1050" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_type</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1051"><a href="#cb1-1051" aria-hidden="true" tabindex="-1"></a><span class="co"># transformers processor class</span></span>
|
||||
<span id="cb1-1052"><a href="#cb1-1052" aria-hidden="true" tabindex="-1"></a><span class="fu">processor_type</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1053"><a href="#cb1-1053" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to save jinja files for tokenizer, transformers default is True</span></span>
|
||||
<span id="cb1-1054"><a href="#cb1-1054" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_save_jinja_files</span><span class="kw">:</span><span class="at"> bool | None = True</span></span>
|
||||
<span id="cb1-1055"><a href="#cb1-1055" aria-hidden="true" tabindex="-1"></a><span class="co"># Trust remote code for untrusted source</span></span>
|
||||
<span id="cb1-1056"><a href="#cb1-1056" aria-hidden="true" tabindex="-1"></a><span class="fu">trust_remote_code</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1057"><a href="#cb1-1057" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1058"><a href="#cb1-1058" aria-hidden="true" tabindex="-1"></a><span class="co"># Don't move the model to the device before sharding. Set to `false` to revert to legacy</span></span>
|
||||
<span id="cb1-1059"><a href="#cb1-1059" aria-hidden="true" tabindex="-1"></a><span class="co"># behavior.</span></span>
|
||||
<span id="cb1-1060"><a href="#cb1-1060" aria-hidden="true" tabindex="-1"></a><span class="fu">experimental_skip_move_to_device</span><span class="kw">:</span><span class="at"> bool | None = True</span></span>
|
||||
<span id="cb1-1061"><a href="#cb1-1061" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1062"><a href="#cb1-1062" aria-hidden="true" tabindex="-1"></a><span class="co"># Use custom kernels, e.g. MegaBlocks.</span></span>
|
||||
<span id="cb1-1063"><a href="#cb1-1063" aria-hidden="true" tabindex="-1"></a><span class="fu">use_kernels</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1064"><a href="#cb1-1064" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1065"><a href="#cb1-1065" aria-hidden="true" tabindex="-1"></a><span class="co"># Model loading quantization config</span></span>
|
||||
<span id="cb1-1066"><a href="#cb1-1066" aria-hidden="true" tabindex="-1"></a><span class="fu">model_quantization_config</span><span class="kw">:</span><span class="at"> Literal['Mxfp4Config'] | None</span></span>
|
||||
<span id="cb1-1067"><a href="#cb1-1067" aria-hidden="true" tabindex="-1"></a><span class="co"># kwargs for model quantization config</span></span>
|
||||
<span id="cb1-1068"><a href="#cb1-1068" aria-hidden="true" tabindex="-1"></a><span class="fu">model_quantization_config_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1069"><a href="#cb1-1069" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1070"><a href="#cb1-1070" aria-hidden="true" tabindex="-1"></a><span class="co"># Where to save the full-finetuned model to</span></span>
|
||||
<span id="cb1-1071"><a href="#cb1-1071" aria-hidden="true" tabindex="-1"></a><span class="fu">output_dir</span><span class="kw">:</span><span class="at"> str = ./model-out</span></span>
|
||||
<span id="cb1-1072"><a href="#cb1-1072" aria-hidden="true" tabindex="-1"></a><span class="co"># push checkpoints to hub</span></span>
|
||||
<span id="cb1-1073"><a href="#cb1-1073" aria-hidden="true" tabindex="-1"></a><span class="fu">hub_model_id</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1074"><a href="#cb1-1074" aria-hidden="true" tabindex="-1"></a><span class="co"># how to push checkpoints to hub</span></span>
|
||||
<span id="cb1-1075"><a href="#cb1-1075" aria-hidden="true" tabindex="-1"></a><span class="fu">hub_strategy</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1076"><a href="#cb1-1076" aria-hidden="true" tabindex="-1"></a><span class="co"># Save model as safetensors (require safetensors package). Default True</span></span>
|
||||
<span id="cb1-1077"><a href="#cb1-1077" aria-hidden="true" tabindex="-1"></a><span class="fu">save_safetensors</span><span class="kw">:</span><span class="at"> bool | None = True</span></span>
|
||||
<span id="cb1-1078"><a href="#cb1-1078" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1079"><a href="#cb1-1079" aria-hidden="true" tabindex="-1"></a><span class="co"># This will attempt to quantize the model down to 8 bits and use adam 8 bit optimizer</span></span>
|
||||
<span id="cb1-1080"><a href="#cb1-1080" aria-hidden="true" tabindex="-1"></a><span class="fu">load_in_8bit</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1081"><a href="#cb1-1081" aria-hidden="true" tabindex="-1"></a><span class="co"># Use bitsandbytes 4 bit</span></span>
|
||||
<span id="cb1-1082"><a href="#cb1-1082" aria-hidden="true" tabindex="-1"></a><span class="fu">load_in_4bit</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1083"><a href="#cb1-1083" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1084"><a href="#cb1-1084" aria-hidden="true" tabindex="-1"></a><span class="co"># If you want to use 'lora' or 'qlora' or leave blank to train all parameters in</span></span>
|
||||
<span id="cb1-1085"><a href="#cb1-1085" aria-hidden="true" tabindex="-1"></a><span class="co"># original model</span></span>
|
||||
<span id="cb1-1086"><a href="#cb1-1086" aria-hidden="true" tabindex="-1"></a><span class="fu">adapter</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1087"><a href="#cb1-1087" aria-hidden="true" tabindex="-1"></a><span class="co"># If you already have a lora model trained that you want to load, put that here. This</span></span>
|
||||
<span id="cb1-1088"><a href="#cb1-1088" aria-hidden="true" tabindex="-1"></a><span class="co"># means after training, if you want to test the model, you should set this to the value</span></span>
|
||||
<span id="cb1-1089"><a href="#cb1-1089" aria-hidden="true" tabindex="-1"></a><span class="co"># of `output_dir`. Note that if you merge an adapter to the base model, a new</span></span>
|
||||
<span id="cb1-1090"><a href="#cb1-1090" aria-hidden="true" tabindex="-1"></a><span class="co"># subdirectory `merged` will be created under the `output_dir`.</span></span>
|
||||
<span id="cb1-1091"><a href="#cb1-1091" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_model_dir</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1092"><a href="#cb1-1092" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_r</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1093"><a href="#cb1-1093" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_alpha</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1094"><a href="#cb1-1094" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_fan_in_fan_out</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1095"><a href="#cb1-1095" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_modules</span><span class="kw">:</span><span class="at"> str | list[str] | None</span></span>
|
||||
<span id="cb1-1096"><a href="#cb1-1096" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_parameters</span><span class="kw">:</span><span class="at"> str | list[str] | None</span></span>
|
||||
<span id="cb1-1097"><a href="#cb1-1097" aria-hidden="true" tabindex="-1"></a><span class="co"># If true, will target all linear modules</span></span>
|
||||
<span id="cb1-1098"><a href="#cb1-1098" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_linear</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1099"><a href="#cb1-1099" aria-hidden="true" tabindex="-1"></a><span class="co"># If you added new tokens to the tokenizer, you may need to save some LoRA modules</span></span>
|
||||
<span id="cb1-1100"><a href="#cb1-1100" aria-hidden="true" tabindex="-1"></a><span class="co"># because they need to know the new tokens. For LLaMA and Mistral, you need to save</span></span>
|
||||
<span id="cb1-1101"><a href="#cb1-1101" aria-hidden="true" tabindex="-1"></a><span class="co"># `embed_tokens` and `lm_head`. It may vary for other models. `embed_tokens` converts</span></span>
|
||||
<span id="cb1-1102"><a href="#cb1-1102" aria-hidden="true" tabindex="-1"></a><span class="co"># tokens to embeddings, and `lm_head` converts embeddings to token probabilities.</span></span>
|
||||
<span id="cb1-1103"><a href="#cb1-1103" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_modules_to_save</span><span class="kw">:</span><span class="at"> list[str] | None</span></span>
|
||||
<span id="cb1-1104"><a href="#cb1-1104" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_dropout</span><span class="kw">:</span><span class="at"> float | None = 0.0</span></span>
|
||||
<span id="cb1-1105"><a href="#cb1-1105" aria-hidden="true" tabindex="-1"></a><span class="co"># The layer indices to transform, otherwise, apply to all layers</span></span>
|
||||
<span id="cb1-1106"><a href="#cb1-1106" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_layers_to_transform</span><span class="kw">:</span><span class="at"> list[int] | None</span></span>
|
||||
<span id="cb1-1107"><a href="#cb1-1107" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_layers_pattern</span><span class="kw">:</span><span class="at"> list[str] | None</span></span>
|
||||
<span id="cb1-1108"><a href="#cb1-1108" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1109"><a href="#cb1-1109" aria-hidden="true" tabindex="-1"></a><span class="fu">peft</span><span class="kw">:</span><span class="at"> PeftConfig | None</span></span>
|
||||
<span id="cb1-1110"><a href="#cb1-1110" aria-hidden="true" tabindex="-1"></a><span class="co"> # For PeftConfig:</span></span>
|
||||
<span id="cb1-1111"><a href="#cb1-1111" aria-hidden="true" tabindex="-1"></a><span class="co"> # Configuration options for loftq initialization for LoRA</span></span>
|
||||
<span id="cb1-1112"><a href="#cb1-1112" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">loftq_config</span><span class="kw">:</span><span class="at"> LoftQConfig | None</span></span>
|
||||
<span id="cb1-1113"><a href="#cb1-1113" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LoftQConfig:</span></span>
|
||||
<span id="cb1-1114"><a href="#cb1-1114" aria-hidden="true" tabindex="-1"></a><span class="co"> # typically 4 bits</span></span>
|
||||
<span id="cb1-1115"><a href="#cb1-1115" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">loftq_bits</span><span class="kw">:</span><span class="at"> int = 4</span></span>
|
||||
<span id="cb1-1116"><a href="#cb1-1116" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1117"><a href="#cb1-1117" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use DoRA.</span></span>
|
||||
<span id="cb1-1118"><a href="#cb1-1118" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_use_dora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1119"><a href="#cb1-1119" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use RSLoRA.</span></span>
|
||||
<span id="cb1-1120"><a href="#cb1-1120" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_use_rslora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1121"><a href="#cb1-1121" aria-hidden="true" tabindex="-1"></a><span class="co"># List of layer indices to replicate.</span></span>
|
||||
<span id="cb1-1122"><a href="#cb1-1122" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_layer_replication</span><span class="kw">:</span><span class="at"> list[tuple[int, int]] | None</span></span>
|
||||
<span id="cb1-1123"><a href="#cb1-1123" aria-hidden="true" tabindex="-1"></a><span class="co"># How to initialize LoRA weights. Default to True which is MS original implementation.</span></span>
|
||||
<span id="cb1-1124"><a href="#cb1-1124" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_init_lora_weights</span><span class="kw">:</span><span class="at"> bool | str | None</span></span>
|
||||
<span id="cb1-1125"><a href="#cb1-1125" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1126"><a href="#cb1-1126" aria-hidden="true" tabindex="-1"></a><span class="co"># load qlora model in sharded format for FSDP using answer.ai technique.</span></span>
|
||||
<span id="cb1-1127"><a href="#cb1-1127" aria-hidden="true" tabindex="-1"></a><span class="fu">qlora_sharded_model_loading</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1128"><a href="#cb1-1128" aria-hidden="true" tabindex="-1"></a><span class="co"># Do the LoRA/PEFT loading on CPU -- this is required if the base model is so large it</span></span>
|
||||
<span id="cb1-1129"><a href="#cb1-1129" aria-hidden="true" tabindex="-1"></a><span class="co"># takes up most or all of the available GPU VRAM, e.g. during a model and LoRA merge</span></span>
|
||||
<span id="cb1-1130"><a href="#cb1-1130" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_on_cpu</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1131"><a href="#cb1-1131" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether you are training a 4-bit GPTQ quantized model</span></span>
|
||||
<span id="cb1-1132"><a href="#cb1-1132" aria-hidden="true" tabindex="-1"></a><span class="fu">gptq</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1133"><a href="#cb1-1133" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the bnb 4bit quantization configuration</span></span>
|
||||
<span id="cb1-1134"><a href="#cb1-1134" aria-hidden="true" tabindex="-1"></a><span class="fu">bnb_config_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1135"><a href="#cb1-1135" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1136"><a href="#cb1-1136" aria-hidden="true" tabindex="-1"></a><span class="co"># loraplus learning rate ratio lr_B / lr_A. Recommended value is 2^4.</span></span>
|
||||
<span id="cb1-1137"><a href="#cb1-1137" aria-hidden="true" tabindex="-1"></a><span class="fu">loraplus_lr_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1138"><a href="#cb1-1138" aria-hidden="true" tabindex="-1"></a><span class="co"># loraplus learning rate for lora embedding layers. Default value is 1e-6.</span></span>
|
||||
<span id="cb1-1139"><a href="#cb1-1139" aria-hidden="true" tabindex="-1"></a><span class="fu">loraplus_lr_embedding</span><span class="kw">:</span><span class="at"> float | None = 1e-06</span></span>
|
||||
<span id="cb1-1140"><a href="#cb1-1140" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1141"><a href="#cb1-1141" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use ReLoRA. Use with jagged_restart_*steps options.</span></span>
|
||||
<span id="cb1-1142"><a href="#cb1-1142" aria-hidden="true" tabindex="-1"></a><span class="fu">relora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1143"><a href="#cb1-1143" aria-hidden="true" tabindex="-1"></a><span class="co"># threshold for optimizer magnitude when pruning</span></span>
|
||||
<span id="cb1-1144"><a href="#cb1-1144" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_prune_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1145"><a href="#cb1-1145" aria-hidden="true" tabindex="-1"></a><span class="co"># True to perform lora weight merges on cpu during restarts, for modest gpu memory</span></span>
|
||||
<span id="cb1-1146"><a href="#cb1-1146" aria-hidden="true" tabindex="-1"></a><span class="co"># savings</span></span>
|
||||
<span id="cb1-1147"><a href="#cb1-1147" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_cpu_offload</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1148"><a href="#cb1-1148" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1149"><a href="#cb1-1149" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to reset for jagged restarts</span></span>
|
||||
<span id="cb1-1150"><a href="#cb1-1150" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1151"><a href="#cb1-1151" aria-hidden="true" tabindex="-1"></a><span class="co"># how many warmup steps to take after reset for jagged restarts</span></span>
|
||||
<span id="cb1-1152"><a href="#cb1-1152" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_warmup_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1153"><a href="#cb1-1153" aria-hidden="true" tabindex="-1"></a><span class="co"># how many anneal steps to take before reset for jagged restarts</span></span>
|
||||
<span id="cb1-1154"><a href="#cb1-1154" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_anneal_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1155"><a href="#cb1-1155" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1156"><a href="#cb1-1156" aria-hidden="true" tabindex="-1"></a><span class="co"># If greater than 1, backpropagation will be skipped and the gradients will be</span></span>
|
||||
<span id="cb1-1157"><a href="#cb1-1157" aria-hidden="true" tabindex="-1"></a><span class="co"># accumulated for the given number of steps.</span></span>
|
||||
<span id="cb1-1158"><a href="#cb1-1158" aria-hidden="true" tabindex="-1"></a><span class="fu">gradient_accumulation_steps</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1159"><a href="#cb1-1159" aria-hidden="true" tabindex="-1"></a><span class="co"># The number of samples to include in each batch. This is the number of samples sent to</span></span>
|
||||
<span id="cb1-1160"><a href="#cb1-1160" aria-hidden="true" tabindex="-1"></a><span class="co"># each GPU. Batch size per gpu = micro_batch_size * gradient_accumulation_steps</span></span>
|
||||
<span id="cb1-1161"><a href="#cb1-1161" aria-hidden="true" tabindex="-1"></a><span class="fu">micro_batch_size</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1162"><a href="#cb1-1162" aria-hidden="true" tabindex="-1"></a><span class="co"># Total batch size, we do not recommended setting this manually</span></span>
|
||||
<span id="cb1-1163"><a href="#cb1-1163" aria-hidden="true" tabindex="-1"></a><span class="fu">batch_size</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1164"><a href="#cb1-1164" aria-hidden="true" tabindex="-1"></a><span class="co"># per gpu micro batch size for evals, defaults to value of micro_batch_size</span></span>
|
||||
<span id="cb1-1165"><a href="#cb1-1165" aria-hidden="true" tabindex="-1"></a><span class="fu">eval_batch_size</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1166"><a href="#cb1-1166" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1167"><a href="#cb1-1167" aria-hidden="true" tabindex="-1"></a><span class="co"># whether to find batch size that fits in memory. Passed to underlying transformers</span></span>
|
||||
<span id="cb1-1168"><a href="#cb1-1168" aria-hidden="true" tabindex="-1"></a><span class="co"># Trainer</span></span>
|
||||
<span id="cb1-1169"><a href="#cb1-1169" aria-hidden="true" tabindex="-1"></a><span class="fu">auto_find_batch_size</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1170"><a href="#cb1-1170" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1171"><a href="#cb1-1171" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to mask out or include the human's prompt from the training labels</span></span>
|
||||
<span id="cb1-1172"><a href="#cb1-1172" aria-hidden="true" tabindex="-1"></a><span class="fu">train_on_inputs</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1173"><a href="#cb1-1173" aria-hidden="true" tabindex="-1"></a><span class="co"># Group similarly sized data to minimize padding. May be slower to start, as it must</span></span>
|
||||
<span id="cb1-1174"><a href="#cb1-1174" aria-hidden="true" tabindex="-1"></a><span class="co"># download and sort the entire dataset. Note that training loss may have an oscillating</span></span>
|
||||
<span id="cb1-1175"><a href="#cb1-1175" aria-hidden="true" tabindex="-1"></a><span class="co"># pattern with this enabled.</span></span>
|
||||
<span id="cb1-1176"><a href="#cb1-1176" aria-hidden="true" tabindex="-1"></a><span class="fu">group_by_length</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1177"><a href="#cb1-1177" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1178"><a href="#cb1-1178" aria-hidden="true" tabindex="-1"></a><span class="fu">learning_rate</span><span class="kw">:</span><span class="at"> str | float (required)</span></span>
|
||||
<span id="cb1-1179"><a href="#cb1-1179" aria-hidden="true" tabindex="-1"></a><span class="fu">embedding_lr</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1180"><a href="#cb1-1180" aria-hidden="true" tabindex="-1"></a><span class="fu">embedding_lr_scale</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1181"><a href="#cb1-1181" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify weight decay</span></span>
|
||||
<span id="cb1-1182"><a href="#cb1-1182" aria-hidden="true" tabindex="-1"></a><span class="fu">weight_decay</span><span class="kw">:</span><span class="at"> float | None = 0.0</span></span>
|
||||
<span id="cb1-1183"><a href="#cb1-1183" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify optimizer</span></span>
|
||||
<span id="cb1-1184"><a href="#cb1-1184" aria-hidden="true" tabindex="-1"></a><span class="fu">optimizer</span><span class="kw">:</span><span class="at"> OptimizerNames | CustomSupportedOptimizers | None = OptimizerNames.ADAMW_TORCH_FUSED</span></span>
|
||||
<span id="cb1-1185"><a href="#cb1-1185" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary of arguments to pass to the optimizer</span></span>
|
||||
<span id="cb1-1186"><a href="#cb1-1186" aria-hidden="true" tabindex="-1"></a><span class="fu">optim_args</span><span class="kw">:</span><span class="at"> str | dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1187"><a href="#cb1-1187" aria-hidden="true" tabindex="-1"></a><span class="co"># The target modules to optimize, i.e. the module names that you would like to train,</span></span>
|
||||
<span id="cb1-1188"><a href="#cb1-1188" aria-hidden="true" tabindex="-1"></a><span class="co"># right now this is used only for GaLore algorithm</span></span>
|
||||
<span id="cb1-1189"><a href="#cb1-1189" aria-hidden="true" tabindex="-1"></a><span class="fu">optim_target_modules</span><span class="kw">:</span><span class="at"> list[str] | Literal['all_linear'] | None</span></span>
|
||||
<span id="cb1-1190"><a href="#cb1-1190" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
|
||||
<span id="cb1-1191"><a href="#cb1-1191" aria-hidden="true" tabindex="-1"></a><span class="fu">torchdistx_path</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1192"><a href="#cb1-1192" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_scheduler</span><span class="kw">:</span><span class="at"> SchedulerType | Literal['one_cycle'] | Literal['rex'] | None = SchedulerType.COSINE</span></span>
|
||||
<span id="cb1-1193"><a href="#cb1-1193" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify a scheduler and kwargs to use with the optimizer</span></span>
|
||||
<span id="cb1-1194"><a href="#cb1-1194" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_scheduler_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1195"><a href="#cb1-1195" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_quadratic_warmup</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1196"><a href="#cb1-1196" aria-hidden="true" tabindex="-1"></a><span class="co"># decay lr to some percentage of the peak lr, e.g. cosine_min_lr_ratio=0.1 for 10% of</span></span>
|
||||
<span id="cb1-1197"><a href="#cb1-1197" aria-hidden="true" tabindex="-1"></a><span class="co"># peak lr</span></span>
|
||||
<span id="cb1-1198"><a href="#cb1-1198" aria-hidden="true" tabindex="-1"></a><span class="fu">cosine_min_lr_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1199"><a href="#cb1-1199" aria-hidden="true" tabindex="-1"></a><span class="co"># freeze lr at some percentage of the step, e.g. cosine_constant_lr_ratio=0.8 means</span></span>
|
||||
<span id="cb1-1200"><a href="#cb1-1200" aria-hidden="true" tabindex="-1"></a><span class="co"># start cosine_min_lr at 80% of training step</span></span>
|
||||
<span id="cb1-1201"><a href="#cb1-1201" aria-hidden="true" tabindex="-1"></a><span class="fu">cosine_constant_lr_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1202"><a href="#cb1-1202" aria-hidden="true" tabindex="-1"></a><span class="co"># Learning rate div factor</span></span>
|
||||
<span id="cb1-1203"><a href="#cb1-1203" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_div_factor</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1204"><a href="#cb1-1204" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1205"><a href="#cb1-1205" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_groups</span><span class="kw">:</span><span class="at"> list[LrGroup] | None</span></span>
|
||||
<span id="cb1-1206"><a href="#cb1-1206" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LrGroup:</span></span>
|
||||
<span id="cb1-1207"><a href="#cb1-1207" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">name</span><span class="kw">:</span><span class="at"> str (required)</span></span>
|
||||
<span id="cb1-1208"><a href="#cb1-1208" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">modules</span><span class="kw">:</span><span class="at"> list[str] (required)</span></span>
|
||||
<span id="cb1-1209"><a href="#cb1-1209" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">lr</span><span class="kw">:</span><span class="at"> float (required)</span></span>
|
||||
<span id="cb1-1210"><a href="#cb1-1210" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1211"><a href="#cb1-1211" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1212"><a href="#cb1-1212" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_epsilon</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1213"><a href="#cb1-1213" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1214"><a href="#cb1-1214" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_epsilon2</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1215"><a href="#cb1-1215" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1216"><a href="#cb1-1216" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta1</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1141"><a href="#cb1-1141" aria-hidden="true" tabindex="-1"></a><span class="fu">merge_lora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1142"><a href="#cb1-1142" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1143"><a href="#cb1-1143" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use ReLoRA. Use with jagged_restart_*steps options.</span></span>
|
||||
<span id="cb1-1144"><a href="#cb1-1144" aria-hidden="true" tabindex="-1"></a><span class="fu">relora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1145"><a href="#cb1-1145" aria-hidden="true" tabindex="-1"></a><span class="co"># threshold for optimizer magnitude when pruning</span></span>
|
||||
<span id="cb1-1146"><a href="#cb1-1146" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_prune_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1147"><a href="#cb1-1147" aria-hidden="true" tabindex="-1"></a><span class="co"># True to perform lora weight merges on cpu during restarts, for modest gpu memory</span></span>
|
||||
<span id="cb1-1148"><a href="#cb1-1148" aria-hidden="true" tabindex="-1"></a><span class="co"># savings</span></span>
|
||||
<span id="cb1-1149"><a href="#cb1-1149" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_cpu_offload</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1150"><a href="#cb1-1150" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1151"><a href="#cb1-1151" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to reset for jagged restarts</span></span>
|
||||
<span id="cb1-1152"><a href="#cb1-1152" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1153"><a href="#cb1-1153" aria-hidden="true" tabindex="-1"></a><span class="co"># how many warmup steps to take after reset for jagged restarts</span></span>
|
||||
<span id="cb1-1154"><a href="#cb1-1154" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_warmup_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1155"><a href="#cb1-1155" aria-hidden="true" tabindex="-1"></a><span class="co"># how many anneal steps to take before reset for jagged restarts</span></span>
|
||||
<span id="cb1-1156"><a href="#cb1-1156" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_anneal_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1157"><a href="#cb1-1157" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1158"><a href="#cb1-1158" aria-hidden="true" tabindex="-1"></a><span class="co"># If greater than 1, backpropagation will be skipped and the gradients will be</span></span>
|
||||
<span id="cb1-1159"><a href="#cb1-1159" aria-hidden="true" tabindex="-1"></a><span class="co"># accumulated for the given number of steps.</span></span>
|
||||
<span id="cb1-1160"><a href="#cb1-1160" aria-hidden="true" tabindex="-1"></a><span class="fu">gradient_accumulation_steps</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1161"><a href="#cb1-1161" aria-hidden="true" tabindex="-1"></a><span class="co"># The number of samples to include in each batch. This is the number of samples sent to</span></span>
|
||||
<span id="cb1-1162"><a href="#cb1-1162" aria-hidden="true" tabindex="-1"></a><span class="co"># each GPU. Batch size per gpu = micro_batch_size * gradient_accumulation_steps</span></span>
|
||||
<span id="cb1-1163"><a href="#cb1-1163" aria-hidden="true" tabindex="-1"></a><span class="fu">micro_batch_size</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1164"><a href="#cb1-1164" aria-hidden="true" tabindex="-1"></a><span class="co"># Total batch size, we do not recommended setting this manually</span></span>
|
||||
<span id="cb1-1165"><a href="#cb1-1165" aria-hidden="true" tabindex="-1"></a><span class="fu">batch_size</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1166"><a href="#cb1-1166" aria-hidden="true" tabindex="-1"></a><span class="co"># per gpu micro batch size for evals, defaults to value of micro_batch_size</span></span>
|
||||
<span id="cb1-1167"><a href="#cb1-1167" aria-hidden="true" tabindex="-1"></a><span class="fu">eval_batch_size</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1168"><a href="#cb1-1168" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1169"><a href="#cb1-1169" aria-hidden="true" tabindex="-1"></a><span class="co"># whether to find batch size that fits in memory. Passed to underlying transformers</span></span>
|
||||
<span id="cb1-1170"><a href="#cb1-1170" aria-hidden="true" tabindex="-1"></a><span class="co"># Trainer</span></span>
|
||||
<span id="cb1-1171"><a href="#cb1-1171" aria-hidden="true" tabindex="-1"></a><span class="fu">auto_find_batch_size</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1172"><a href="#cb1-1172" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1173"><a href="#cb1-1173" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to mask out or include the human's prompt from the training labels</span></span>
|
||||
<span id="cb1-1174"><a href="#cb1-1174" aria-hidden="true" tabindex="-1"></a><span class="fu">train_on_inputs</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1175"><a href="#cb1-1175" aria-hidden="true" tabindex="-1"></a><span class="co"># Group similarly sized data to minimize padding. May be slower to start, as it must</span></span>
|
||||
<span id="cb1-1176"><a href="#cb1-1176" aria-hidden="true" tabindex="-1"></a><span class="co"># download and sort the entire dataset. Note that training loss may have an oscillating</span></span>
|
||||
<span id="cb1-1177"><a href="#cb1-1177" aria-hidden="true" tabindex="-1"></a><span class="co"># pattern with this enabled.</span></span>
|
||||
<span id="cb1-1178"><a href="#cb1-1178" aria-hidden="true" tabindex="-1"></a><span class="fu">group_by_length</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1179"><a href="#cb1-1179" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1180"><a href="#cb1-1180" aria-hidden="true" tabindex="-1"></a><span class="fu">learning_rate</span><span class="kw">:</span><span class="at"> str | float (required)</span></span>
|
||||
<span id="cb1-1181"><a href="#cb1-1181" aria-hidden="true" tabindex="-1"></a><span class="fu">embedding_lr</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1182"><a href="#cb1-1182" aria-hidden="true" tabindex="-1"></a><span class="fu">embedding_lr_scale</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1183"><a href="#cb1-1183" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify weight decay</span></span>
|
||||
<span id="cb1-1184"><a href="#cb1-1184" aria-hidden="true" tabindex="-1"></a><span class="fu">weight_decay</span><span class="kw">:</span><span class="at"> float | None = 0.0</span></span>
|
||||
<span id="cb1-1185"><a href="#cb1-1185" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify optimizer</span></span>
|
||||
<span id="cb1-1186"><a href="#cb1-1186" aria-hidden="true" tabindex="-1"></a><span class="fu">optimizer</span><span class="kw">:</span><span class="at"> OptimizerNames | CustomSupportedOptimizers | None = OptimizerNames.ADAMW_TORCH_FUSED</span></span>
|
||||
<span id="cb1-1187"><a href="#cb1-1187" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary of arguments to pass to the optimizer</span></span>
|
||||
<span id="cb1-1188"><a href="#cb1-1188" aria-hidden="true" tabindex="-1"></a><span class="fu">optim_args</span><span class="kw">:</span><span class="at"> str | dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1189"><a href="#cb1-1189" aria-hidden="true" tabindex="-1"></a><span class="co"># The target modules to optimize, i.e. the module names that you would like to train,</span></span>
|
||||
<span id="cb1-1190"><a href="#cb1-1190" aria-hidden="true" tabindex="-1"></a><span class="co"># right now this is used only for GaLore algorithm</span></span>
|
||||
<span id="cb1-1191"><a href="#cb1-1191" aria-hidden="true" tabindex="-1"></a><span class="fu">optim_target_modules</span><span class="kw">:</span><span class="at"> list[str] | Literal['all_linear'] | None</span></span>
|
||||
<span id="cb1-1192"><a href="#cb1-1192" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
|
||||
<span id="cb1-1193"><a href="#cb1-1193" aria-hidden="true" tabindex="-1"></a><span class="fu">torchdistx_path</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1194"><a href="#cb1-1194" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_scheduler</span><span class="kw">:</span><span class="at"> SchedulerType | Literal['one_cycle'] | Literal['rex'] | None = SchedulerType.COSINE</span></span>
|
||||
<span id="cb1-1195"><a href="#cb1-1195" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify a scheduler and kwargs to use with the optimizer</span></span>
|
||||
<span id="cb1-1196"><a href="#cb1-1196" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_scheduler_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1197"><a href="#cb1-1197" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_quadratic_warmup</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1198"><a href="#cb1-1198" aria-hidden="true" tabindex="-1"></a><span class="co"># decay lr to some percentage of the peak lr, e.g. cosine_min_lr_ratio=0.1 for 10% of</span></span>
|
||||
<span id="cb1-1199"><a href="#cb1-1199" aria-hidden="true" tabindex="-1"></a><span class="co"># peak lr</span></span>
|
||||
<span id="cb1-1200"><a href="#cb1-1200" aria-hidden="true" tabindex="-1"></a><span class="fu">cosine_min_lr_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1201"><a href="#cb1-1201" aria-hidden="true" tabindex="-1"></a><span class="co"># freeze lr at some percentage of the step, e.g. cosine_constant_lr_ratio=0.8 means</span></span>
|
||||
<span id="cb1-1202"><a href="#cb1-1202" aria-hidden="true" tabindex="-1"></a><span class="co"># start cosine_min_lr at 80% of training step</span></span>
|
||||
<span id="cb1-1203"><a href="#cb1-1203" aria-hidden="true" tabindex="-1"></a><span class="fu">cosine_constant_lr_ratio</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1204"><a href="#cb1-1204" aria-hidden="true" tabindex="-1"></a><span class="co"># Learning rate div factor</span></span>
|
||||
<span id="cb1-1205"><a href="#cb1-1205" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_div_factor</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1206"><a href="#cb1-1206" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1207"><a href="#cb1-1207" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_groups</span><span class="kw">:</span><span class="at"> list[LrGroup] | None</span></span>
|
||||
<span id="cb1-1208"><a href="#cb1-1208" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LrGroup:</span></span>
|
||||
<span id="cb1-1209"><a href="#cb1-1209" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">name</span><span class="kw">:</span><span class="at"> str (required)</span></span>
|
||||
<span id="cb1-1210"><a href="#cb1-1210" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">modules</span><span class="kw">:</span><span class="at"> list[str] (required)</span></span>
|
||||
<span id="cb1-1211"><a href="#cb1-1211" aria-hidden="true" tabindex="-1"></a><span class="at"> </span><span class="fu">lr</span><span class="kw">:</span><span class="at"> float (required)</span></span>
|
||||
<span id="cb1-1212"><a href="#cb1-1212" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1213"><a href="#cb1-1213" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1214"><a href="#cb1-1214" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_epsilon</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1215"><a href="#cb1-1215" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1216"><a href="#cb1-1216" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_epsilon2</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1217"><a href="#cb1-1217" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1218"><a href="#cb1-1218" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta2</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1219"><a href="#cb1-1219" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1220"><a href="#cb1-1220" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta3</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1221"><a href="#cb1-1221" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1222"><a href="#cb1-1222" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer learning rate</span></span>
|
||||
<span id="cb1-1223"><a href="#cb1-1223" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_lr</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1224"><a href="#cb1-1224" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer momentum</span></span>
|
||||
<span id="cb1-1225"><a href="#cb1-1225" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_momentum</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1226"><a href="#cb1-1226" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: r/d fraction for low-rank approximation. Used to compute the low-rank</span></span>
|
||||
<span id="cb1-1227"><a href="#cb1-1227" aria-hidden="true" tabindex="-1"></a><span class="co"># dimension.</span></span>
|
||||
<span id="cb1-1228"><a href="#cb1-1228" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_fraction</span><span class="kw">:</span><span class="at"> float | None = 1.0</span></span>
|
||||
<span id="cb1-1229"><a href="#cb1-1229" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: Round up the low-rank dimension to a multiple of this number. This may</span></span>
|
||||
<span id="cb1-1230"><a href="#cb1-1230" aria-hidden="true" tabindex="-1"></a><span class="co"># be useful to ensure even sharding.</span></span>
|
||||
<span id="cb1-1231"><a href="#cb1-1231" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_multiple_of</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1232"><a href="#cb1-1232" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1233"><a href="#cb1-1233" aria-hidden="true" tabindex="-1"></a><span class="co"># Gradient clipping max norm</span></span>
|
||||
<span id="cb1-1234"><a href="#cb1-1234" aria-hidden="true" tabindex="-1"></a><span class="fu">max_grad_norm</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1235"><a href="#cb1-1235" aria-hidden="true" tabindex="-1"></a><span class="fu">num_epochs</span><span class="kw">:</span><span class="at"> float = 1.0</span></span>
|
||||
<span id="cb1-1236"><a href="#cb1-1236" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1237"><a href="#cb1-1237" aria-hidden="true" tabindex="-1"></a><span class="fu">use_wandb</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1238"><a href="#cb1-1238" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your wandb run</span></span>
|
||||
<span id="cb1-1239"><a href="#cb1-1239" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1240"><a href="#cb1-1240" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the ID of your wandb run</span></span>
|
||||
<span id="cb1-1241"><a href="#cb1-1241" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_run_id</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1242"><a href="#cb1-1242" aria-hidden="true" tabindex="-1"></a><span class="co"># "offline" to save run metadata locally and not sync to the server, "disabled" to turn</span></span>
|
||||
<span id="cb1-1243"><a href="#cb1-1243" aria-hidden="true" tabindex="-1"></a><span class="co"># off wandb</span></span>
|
||||
<span id="cb1-1244"><a href="#cb1-1244" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_mode</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1245"><a href="#cb1-1245" aria-hidden="true" tabindex="-1"></a><span class="co"># Your wandb project name</span></span>
|
||||
<span id="cb1-1246"><a href="#cb1-1246" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_project</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1247"><a href="#cb1-1247" aria-hidden="true" tabindex="-1"></a><span class="co"># A wandb Team name if using a Team</span></span>
|
||||
<span id="cb1-1248"><a href="#cb1-1248" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_entity</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1249"><a href="#cb1-1249" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_watch</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1250"><a href="#cb1-1250" aria-hidden="true" tabindex="-1"></a><span class="co"># "checkpoint" to log model to wandb Artifacts every `save_steps` or "end" to log only</span></span>
|
||||
<span id="cb1-1251"><a href="#cb1-1251" aria-hidden="true" tabindex="-1"></a><span class="co"># at the end of training</span></span>
|
||||
<span id="cb1-1252"><a href="#cb1-1252" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_log_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1253"><a href="#cb1-1253" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1254"><a href="#cb1-1254" aria-hidden="true" tabindex="-1"></a><span class="fu">use_mlflow</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1255"><a href="#cb1-1255" aria-hidden="true" tabindex="-1"></a><span class="co"># URI to mlflow</span></span>
|
||||
<span id="cb1-1256"><a href="#cb1-1256" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_tracking_uri</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1257"><a href="#cb1-1257" aria-hidden="true" tabindex="-1"></a><span class="co"># Your experiment name</span></span>
|
||||
<span id="cb1-1258"><a href="#cb1-1258" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_experiment_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1259"><a href="#cb1-1259" aria-hidden="true" tabindex="-1"></a><span class="co"># Your run name</span></span>
|
||||
<span id="cb1-1260"><a href="#cb1-1260" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1261"><a href="#cb1-1261" aria-hidden="true" tabindex="-1"></a><span class="co"># set to true to copy each saved checkpoint on each save to mlflow artifact registry</span></span>
|
||||
<span id="cb1-1262"><a href="#cb1-1262" aria-hidden="true" tabindex="-1"></a><span class="fu">hf_mlflow_log_artifacts</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1263"><a href="#cb1-1263" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1264"><a href="#cb1-1264" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable or disable Comet integration.</span></span>
|
||||
<span id="cb1-1265"><a href="#cb1-1265" aria-hidden="true" tabindex="-1"></a><span class="fu">use_comet</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1266"><a href="#cb1-1266" aria-hidden="true" tabindex="-1"></a><span class="co"># API key for Comet. Recommended to set via `comet login`.</span></span>
|
||||
<span id="cb1-1267"><a href="#cb1-1267" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_api_key</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1268"><a href="#cb1-1268" aria-hidden="true" tabindex="-1"></a><span class="co"># Workspace name in Comet. Defaults to the user's default workspace.</span></span>
|
||||
<span id="cb1-1269"><a href="#cb1-1269" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_workspace</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1270"><a href="#cb1-1270" aria-hidden="true" tabindex="-1"></a><span class="co"># Project name in Comet. Defaults to Uncategorized.</span></span>
|
||||
<span id="cb1-1271"><a href="#cb1-1271" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_project_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1272"><a href="#cb1-1272" aria-hidden="true" tabindex="-1"></a><span class="co"># Identifier for the experiment. Used to append data to an existing experiment or</span></span>
|
||||
<span id="cb1-1273"><a href="#cb1-1273" aria-hidden="true" tabindex="-1"></a><span class="co"># control the key of new experiments. Default to a random key.</span></span>
|
||||
<span id="cb1-1274"><a href="#cb1-1274" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_experiment_key</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1275"><a href="#cb1-1275" aria-hidden="true" tabindex="-1"></a><span class="co"># Create a new experiment ("create") or log to an existing one ("get"). Default</span></span>
|
||||
<span id="cb1-1276"><a href="#cb1-1276" aria-hidden="true" tabindex="-1"></a><span class="co"># ("get_or_create") auto-selects based on configuration.</span></span>
|
||||
<span id="cb1-1277"><a href="#cb1-1277" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_mode</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1278"><a href="#cb1-1278" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to True to log data to Comet server, or False for offline storage. Default is</span></span>
|
||||
<span id="cb1-1279"><a href="#cb1-1279" aria-hidden="true" tabindex="-1"></a><span class="co"># True.</span></span>
|
||||
<span id="cb1-1280"><a href="#cb1-1280" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_online</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1281"><a href="#cb1-1281" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary for additional configuration settings, see the doc for more details.</span></span>
|
||||
<span id="cb1-1282"><a href="#cb1-1282" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_experiment_config</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1283"><a href="#cb1-1283" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1284"><a href="#cb1-1284" aria-hidden="true" tabindex="-1"></a><span class="co"># the number of activate layers in LISA</span></span>
|
||||
<span id="cb1-1285"><a href="#cb1-1285" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_n_layers</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1286"><a href="#cb1-1286" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to switch layers in LISA</span></span>
|
||||
<span id="cb1-1287"><a href="#cb1-1287" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_step_interval</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1288"><a href="#cb1-1288" aria-hidden="true" tabindex="-1"></a><span class="co"># path under the model to access the layers</span></span>
|
||||
<span id="cb1-1289"><a href="#cb1-1289" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_layers_attribute</span><span class="kw">:</span><span class="at"> str | None = model.layers</span></span>
|
||||
<span id="cb1-1290"><a href="#cb1-1290" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1291"><a href="#cb1-1291" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_title</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1292"><a href="#cb1-1292" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_share</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1293"><a href="#cb1-1293" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_server_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1294"><a href="#cb1-1294" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_server_port</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1295"><a href="#cb1-1295" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_max_new_tokens</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1296"><a href="#cb1-1296" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_temperature</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1297"><a href="#cb1-1297" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1298"><a href="#cb1-1298" aria-hidden="true" tabindex="-1"></a><span class="fu">use_ray</span><span class="kw">:</span><span class="at"> bool = False</span></span>
|
||||
<span id="cb1-1299"><a href="#cb1-1299" aria-hidden="true" tabindex="-1"></a><span class="fu">ray_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1300"><a href="#cb1-1300" aria-hidden="true" tabindex="-1"></a><span class="fu">ray_num_workers</span><span class="kw">:</span><span class="at"> int = 1</span></span>
|
||||
<span id="cb1-1301"><a href="#cb1-1301" aria-hidden="true" tabindex="-1"></a><span class="fu">resources_per_worker</span><span class="kw">:</span><span class="at"> dict</span></span>
|
||||
<span id="cb1-1302"><a href="#cb1-1302" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1303"><a href="#cb1-1303" aria-hidden="true" tabindex="-1"></a><span class="co"># The size of the image to resize to. It can be an integer (resized into padded-square</span></span>
|
||||
<span id="cb1-1304"><a href="#cb1-1304" aria-hidden="true" tabindex="-1"></a><span class="co"># image) or a tuple (width, height).If not provided, we will attempt to load from</span></span>
|
||||
<span id="cb1-1305"><a href="#cb1-1305" aria-hidden="true" tabindex="-1"></a><span class="co"># preprocessor.size, otherwise, images won't be resized.</span></span>
|
||||
<span id="cb1-1306"><a href="#cb1-1306" aria-hidden="true" tabindex="-1"></a><span class="fu">image_size</span><span class="kw">:</span><span class="at"> int | tuple[int, int] | None</span></span>
|
||||
<span id="cb1-1307"><a href="#cb1-1307" aria-hidden="true" tabindex="-1"></a><span class="co"># The resampling algorithm to use for image resizing. Default is bilinear. Please refer</span></span>
|
||||
<span id="cb1-1308"><a href="#cb1-1308" aria-hidden="true" tabindex="-1"></a><span class="co"># to PIL.Image.Resampling for more details.</span></span>
|
||||
<span id="cb1-1309"><a href="#cb1-1309" aria-hidden="true" tabindex="-1"></a><span class="fu">image_resize_algorithm</span><span class="kw">:</span><span class="at"> Literal['bilinear', 'bicubic', 'lanczos'] | Resampling | None</span></span>
|
||||
<span id="cb1-1310"><a href="#cb1-1310" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1311"><a href="#cb1-1311" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the base model configuration</span></span>
|
||||
<span id="cb1-1312"><a href="#cb1-1312" aria-hidden="true" tabindex="-1"></a><span class="fu">overrides_of_model_config</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1313"><a href="#cb1-1313" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides the base model loading from_pretrained</span></span>
|
||||
<span id="cb1-1314"><a href="#cb1-1314" aria-hidden="true" tabindex="-1"></a><span class="fu">overrides_of_model_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1315"><a href="#cb1-1315" aria-hidden="true" tabindex="-1"></a><span class="co"># If you want to specify the type of model to load, AutoModelForCausalLM is a good</span></span>
|
||||
<span id="cb1-1316"><a href="#cb1-1316" aria-hidden="true" tabindex="-1"></a><span class="co"># choice too</span></span>
|
||||
<span id="cb1-1317"><a href="#cb1-1317" aria-hidden="true" tabindex="-1"></a><span class="fu">type_of_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1318"><a href="#cb1-1318" aria-hidden="true" tabindex="-1"></a><span class="co"># You can specify to choose a specific model revision from huggingface hub</span></span>
|
||||
<span id="cb1-1319"><a href="#cb1-1319" aria-hidden="true" tabindex="-1"></a><span class="fu">revision_of_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1320"><a href="#cb1-1320" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1321"><a href="#cb1-1321" aria-hidden="true" tabindex="-1"></a><span class="fu">max_packed_sequence_len</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1322"><a href="#cb1-1322" aria-hidden="true" tabindex="-1"></a><span class="fu">rope_scaling</span><span class="kw">:</span><span class="at"> Any | None</span></span>
|
||||
<span id="cb1-1323"><a href="#cb1-1323" aria-hidden="true" tabindex="-1"></a><span class="fu">noisy_embedding_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1324"><a href="#cb1-1324" aria-hidden="true" tabindex="-1"></a><span class="fu">dpo_beta</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1325"><a href="#cb1-1325" aria-hidden="true" tabindex="-1"></a><span class="fu">evaluation_strategy</span><span class="kw">:</span><span class="at"> str | None</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
<span id="cb1-1218"><a href="#cb1-1218" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta1</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1219"><a href="#cb1-1219" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1220"><a href="#cb1-1220" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta2</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1221"><a href="#cb1-1221" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1222"><a href="#cb1-1222" aria-hidden="true" tabindex="-1"></a><span class="fu">adam_beta3</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1223"><a href="#cb1-1223" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1224"><a href="#cb1-1224" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer learning rate</span></span>
|
||||
<span id="cb1-1225"><a href="#cb1-1225" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_lr</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1226"><a href="#cb1-1226" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer momentum</span></span>
|
||||
<span id="cb1-1227"><a href="#cb1-1227" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_momentum</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1228"><a href="#cb1-1228" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: r/d fraction for low-rank approximation. Used to compute the low-rank</span></span>
|
||||
<span id="cb1-1229"><a href="#cb1-1229" aria-hidden="true" tabindex="-1"></a><span class="co"># dimension.</span></span>
|
||||
<span id="cb1-1230"><a href="#cb1-1230" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_fraction</span><span class="kw">:</span><span class="at"> float | None = 1.0</span></span>
|
||||
<span id="cb1-1231"><a href="#cb1-1231" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: Round up the low-rank dimension to a multiple of this number. This may</span></span>
|
||||
<span id="cb1-1232"><a href="#cb1-1232" aria-hidden="true" tabindex="-1"></a><span class="co"># be useful to ensure even sharding.</span></span>
|
||||
<span id="cb1-1233"><a href="#cb1-1233" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_multiple_of</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1234"><a href="#cb1-1234" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1235"><a href="#cb1-1235" aria-hidden="true" tabindex="-1"></a><span class="co"># Gradient clipping max norm</span></span>
|
||||
<span id="cb1-1236"><a href="#cb1-1236" aria-hidden="true" tabindex="-1"></a><span class="fu">max_grad_norm</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1237"><a href="#cb1-1237" aria-hidden="true" tabindex="-1"></a><span class="fu">num_epochs</span><span class="kw">:</span><span class="at"> float = 1.0</span></span>
|
||||
<span id="cb1-1238"><a href="#cb1-1238" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1239"><a href="#cb1-1239" aria-hidden="true" tabindex="-1"></a><span class="fu">use_wandb</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1240"><a href="#cb1-1240" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your wandb run</span></span>
|
||||
<span id="cb1-1241"><a href="#cb1-1241" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1242"><a href="#cb1-1242" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the ID of your wandb run</span></span>
|
||||
<span id="cb1-1243"><a href="#cb1-1243" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_run_id</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1244"><a href="#cb1-1244" aria-hidden="true" tabindex="-1"></a><span class="co"># "offline" to save run metadata locally and not sync to the server, "disabled" to turn</span></span>
|
||||
<span id="cb1-1245"><a href="#cb1-1245" aria-hidden="true" tabindex="-1"></a><span class="co"># off wandb</span></span>
|
||||
<span id="cb1-1246"><a href="#cb1-1246" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_mode</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1247"><a href="#cb1-1247" aria-hidden="true" tabindex="-1"></a><span class="co"># Your wandb project name</span></span>
|
||||
<span id="cb1-1248"><a href="#cb1-1248" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_project</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1249"><a href="#cb1-1249" aria-hidden="true" tabindex="-1"></a><span class="co"># A wandb Team name if using a Team</span></span>
|
||||
<span id="cb1-1250"><a href="#cb1-1250" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_entity</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1251"><a href="#cb1-1251" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_watch</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1252"><a href="#cb1-1252" aria-hidden="true" tabindex="-1"></a><span class="co"># "checkpoint" to log model to wandb Artifacts every `save_steps` or "end" to log only</span></span>
|
||||
<span id="cb1-1253"><a href="#cb1-1253" aria-hidden="true" tabindex="-1"></a><span class="co"># at the end of training</span></span>
|
||||
<span id="cb1-1254"><a href="#cb1-1254" aria-hidden="true" tabindex="-1"></a><span class="fu">wandb_log_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1255"><a href="#cb1-1255" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1256"><a href="#cb1-1256" aria-hidden="true" tabindex="-1"></a><span class="fu">use_mlflow</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1257"><a href="#cb1-1257" aria-hidden="true" tabindex="-1"></a><span class="co"># URI to mlflow</span></span>
|
||||
<span id="cb1-1258"><a href="#cb1-1258" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_tracking_uri</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1259"><a href="#cb1-1259" aria-hidden="true" tabindex="-1"></a><span class="co"># Your experiment name</span></span>
|
||||
<span id="cb1-1260"><a href="#cb1-1260" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_experiment_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1261"><a href="#cb1-1261" aria-hidden="true" tabindex="-1"></a><span class="co"># Your run name</span></span>
|
||||
<span id="cb1-1262"><a href="#cb1-1262" aria-hidden="true" tabindex="-1"></a><span class="fu">mlflow_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1263"><a href="#cb1-1263" aria-hidden="true" tabindex="-1"></a><span class="co"># set to true to copy each saved checkpoint on each save to mlflow artifact registry</span></span>
|
||||
<span id="cb1-1264"><a href="#cb1-1264" aria-hidden="true" tabindex="-1"></a><span class="fu">hf_mlflow_log_artifacts</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1265"><a href="#cb1-1265" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1266"><a href="#cb1-1266" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable or disable Comet integration.</span></span>
|
||||
<span id="cb1-1267"><a href="#cb1-1267" aria-hidden="true" tabindex="-1"></a><span class="fu">use_comet</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1268"><a href="#cb1-1268" aria-hidden="true" tabindex="-1"></a><span class="co"># API key for Comet. Recommended to set via `comet login`.</span></span>
|
||||
<span id="cb1-1269"><a href="#cb1-1269" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_api_key</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1270"><a href="#cb1-1270" aria-hidden="true" tabindex="-1"></a><span class="co"># Workspace name in Comet. Defaults to the user's default workspace.</span></span>
|
||||
<span id="cb1-1271"><a href="#cb1-1271" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_workspace</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1272"><a href="#cb1-1272" aria-hidden="true" tabindex="-1"></a><span class="co"># Project name in Comet. Defaults to Uncategorized.</span></span>
|
||||
<span id="cb1-1273"><a href="#cb1-1273" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_project_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1274"><a href="#cb1-1274" aria-hidden="true" tabindex="-1"></a><span class="co"># Identifier for the experiment. Used to append data to an existing experiment or</span></span>
|
||||
<span id="cb1-1275"><a href="#cb1-1275" aria-hidden="true" tabindex="-1"></a><span class="co"># control the key of new experiments. Default to a random key.</span></span>
|
||||
<span id="cb1-1276"><a href="#cb1-1276" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_experiment_key</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1277"><a href="#cb1-1277" aria-hidden="true" tabindex="-1"></a><span class="co"># Create a new experiment ("create") or log to an existing one ("get"). Default</span></span>
|
||||
<span id="cb1-1278"><a href="#cb1-1278" aria-hidden="true" tabindex="-1"></a><span class="co"># ("get_or_create") auto-selects based on configuration.</span></span>
|
||||
<span id="cb1-1279"><a href="#cb1-1279" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_mode</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1280"><a href="#cb1-1280" aria-hidden="true" tabindex="-1"></a><span class="co"># Set to True to log data to Comet server, or False for offline storage. Default is</span></span>
|
||||
<span id="cb1-1281"><a href="#cb1-1281" aria-hidden="true" tabindex="-1"></a><span class="co"># True.</span></span>
|
||||
<span id="cb1-1282"><a href="#cb1-1282" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_online</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1283"><a href="#cb1-1283" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary for additional configuration settings, see the doc for more details.</span></span>
|
||||
<span id="cb1-1284"><a href="#cb1-1284" aria-hidden="true" tabindex="-1"></a><span class="fu">comet_experiment_config</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1285"><a href="#cb1-1285" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1286"><a href="#cb1-1286" aria-hidden="true" tabindex="-1"></a><span class="co"># the number of activate layers in LISA</span></span>
|
||||
<span id="cb1-1287"><a href="#cb1-1287" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_n_layers</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1288"><a href="#cb1-1288" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to switch layers in LISA</span></span>
|
||||
<span id="cb1-1289"><a href="#cb1-1289" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_step_interval</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1290"><a href="#cb1-1290" aria-hidden="true" tabindex="-1"></a><span class="co"># path under the model to access the layers</span></span>
|
||||
<span id="cb1-1291"><a href="#cb1-1291" aria-hidden="true" tabindex="-1"></a><span class="fu">lisa_layers_attribute</span><span class="kw">:</span><span class="at"> str | None = model.layers</span></span>
|
||||
<span id="cb1-1292"><a href="#cb1-1292" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1293"><a href="#cb1-1293" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_title</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1294"><a href="#cb1-1294" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_share</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1295"><a href="#cb1-1295" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_server_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1296"><a href="#cb1-1296" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_server_port</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1297"><a href="#cb1-1297" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_max_new_tokens</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1298"><a href="#cb1-1298" aria-hidden="true" tabindex="-1"></a><span class="fu">gradio_temperature</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1299"><a href="#cb1-1299" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1300"><a href="#cb1-1300" aria-hidden="true" tabindex="-1"></a><span class="fu">use_ray</span><span class="kw">:</span><span class="at"> bool = False</span></span>
|
||||
<span id="cb1-1301"><a href="#cb1-1301" aria-hidden="true" tabindex="-1"></a><span class="fu">ray_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1302"><a href="#cb1-1302" aria-hidden="true" tabindex="-1"></a><span class="fu">ray_num_workers</span><span class="kw">:</span><span class="at"> int = 1</span></span>
|
||||
<span id="cb1-1303"><a href="#cb1-1303" aria-hidden="true" tabindex="-1"></a><span class="fu">resources_per_worker</span><span class="kw">:</span><span class="at"> dict</span></span>
|
||||
<span id="cb1-1304"><a href="#cb1-1304" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1305"><a href="#cb1-1305" aria-hidden="true" tabindex="-1"></a><span class="co"># The size of the image to resize to. It can be an integer (resized into padded-square</span></span>
|
||||
<span id="cb1-1306"><a href="#cb1-1306" aria-hidden="true" tabindex="-1"></a><span class="co"># image) or a tuple (width, height).If not provided, we will attempt to load from</span></span>
|
||||
<span id="cb1-1307"><a href="#cb1-1307" aria-hidden="true" tabindex="-1"></a><span class="co"># preprocessor.size, otherwise, images won't be resized.</span></span>
|
||||
<span id="cb1-1308"><a href="#cb1-1308" aria-hidden="true" tabindex="-1"></a><span class="fu">image_size</span><span class="kw">:</span><span class="at"> int | tuple[int, int] | None</span></span>
|
||||
<span id="cb1-1309"><a href="#cb1-1309" aria-hidden="true" tabindex="-1"></a><span class="co"># The resampling algorithm to use for image resizing. Default is bilinear. Please refer</span></span>
|
||||
<span id="cb1-1310"><a href="#cb1-1310" aria-hidden="true" tabindex="-1"></a><span class="co"># to PIL.Image.Resampling for more details.</span></span>
|
||||
<span id="cb1-1311"><a href="#cb1-1311" aria-hidden="true" tabindex="-1"></a><span class="fu">image_resize_algorithm</span><span class="kw">:</span><span class="at"> Literal['bilinear', 'bicubic', 'lanczos'] | Resampling | None</span></span>
|
||||
<span id="cb1-1312"><a href="#cb1-1312" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1313"><a href="#cb1-1313" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the base model configuration</span></span>
|
||||
<span id="cb1-1314"><a href="#cb1-1314" aria-hidden="true" tabindex="-1"></a><span class="fu">overrides_of_model_config</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1315"><a href="#cb1-1315" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides the base model loading from_pretrained</span></span>
|
||||
<span id="cb1-1316"><a href="#cb1-1316" aria-hidden="true" tabindex="-1"></a><span class="fu">overrides_of_model_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1317"><a href="#cb1-1317" aria-hidden="true" tabindex="-1"></a><span class="co"># If you want to specify the type of model to load, AutoModelForCausalLM is a good</span></span>
|
||||
<span id="cb1-1318"><a href="#cb1-1318" aria-hidden="true" tabindex="-1"></a><span class="co"># choice too</span></span>
|
||||
<span id="cb1-1319"><a href="#cb1-1319" aria-hidden="true" tabindex="-1"></a><span class="fu">type_of_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1320"><a href="#cb1-1320" aria-hidden="true" tabindex="-1"></a><span class="co"># You can specify to choose a specific model revision from huggingface hub</span></span>
|
||||
<span id="cb1-1321"><a href="#cb1-1321" aria-hidden="true" tabindex="-1"></a><span class="fu">revision_of_model</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1322"><a href="#cb1-1322" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1323"><a href="#cb1-1323" aria-hidden="true" tabindex="-1"></a><span class="fu">max_packed_sequence_len</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1324"><a href="#cb1-1324" aria-hidden="true" tabindex="-1"></a><span class="fu">rope_scaling</span><span class="kw">:</span><span class="at"> Any | None</span></span>
|
||||
<span id="cb1-1325"><a href="#cb1-1325" aria-hidden="true" tabindex="-1"></a><span class="fu">noisy_embedding_alpha</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1326"><a href="#cb1-1326" aria-hidden="true" tabindex="-1"></a><span class="fu">dpo_beta</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1327"><a href="#cb1-1327" aria-hidden="true" tabindex="-1"></a><span class="fu">evaluation_strategy</span><span class="kw">:</span><span class="at"> str | None</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
|
||||
|
||||
|
||||
|
||||
|
||||
File diff suppressed because one or more lines are too long
394
sitemap.xml
394
sitemap.xml
@@ -2,790 +2,790 @@
|
||||
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/index.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.734Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.883Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/src/axolotl/integrations/LICENSE.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.739Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.887Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/gradient_checkpointing.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.715Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/mixed_precision.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/sequence_parallelism.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.719Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.867Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/docker.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.715Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/torchao.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.719Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.867Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/multi-gpu.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset_preprocessing.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.715Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/debugging.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.715Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/rlhf.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.867Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/lr_groups.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/multimodal.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/ray-integration.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.867Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/input_output.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.717Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/inference.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.717Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/fsdp_qlora.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.715Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/multipack.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.input_output.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.318Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.093Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_patch_multipack.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.582Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.362Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.art.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.953Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.723Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.quantize.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.030Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.801Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_flash.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.533Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.312Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.profiler.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.119Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.911Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.stepwise_supervised.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.322Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.098Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.cut_cross_entropy.args.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.003Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.793Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.data.sft.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.752Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.537Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.unsloth_.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.599Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.379Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/kernels.geglu.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.509Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.288Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.orpo.chat_template.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.407Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.184Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.utils.sweeps.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.076Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.847Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.delinearize_llama4.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.982Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.753Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.pygmalion.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.339Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.115Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/evaluate.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.734Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.506Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.data.pretraining.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.746Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.530Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/index.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.665Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.437Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.stablelm_attn_hijack_flash.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.588Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.368Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.utils.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.579Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.359Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.checks.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.960Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.730Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.chat_templates.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.646Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.428Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.builders.rl.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.829Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.597Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.messages.chat.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.343Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.119Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.mixins.optimizer.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.190Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.965Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.orcamini.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.333Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.108Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.mixins.scheduler.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.200Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.975Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.utils.fetch.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.064Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.836Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.datasets.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.819Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.605Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.cloud.base.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.040Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.811Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.utils.args.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.059Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.830Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.comet_.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.128Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.920Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.mlflow_.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.124Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.916Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.builders.causal.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.824Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.592Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.train.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.923Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.692Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.integrations.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.848Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.635Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.lm_eval.args.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.018Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.808Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.evaluate.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.931Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.701Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.trainer.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.684Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.468Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.llama3.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.378Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.154Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/convert.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.758Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.530Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.multimodal.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.836Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.623Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/loaders.patch_manager.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.183Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.958Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.training.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.801Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.587Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.config.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.787Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.573Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.user_defined.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.387Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.164Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.bradley_terry.llama3.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.411Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.188Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.vllm_serve.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.036Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.808Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_w_system.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.285Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.060Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.merge_lora.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.005Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.775Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.ctx_managers.sequence_parallel.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.224Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.998Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_instruct.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.274Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.048Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.bench.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.660Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.443Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/common.datasets.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.039Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.830Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.utils.train.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.087Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.859Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_attn_hijack_xformers.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.535Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.314Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.chat.messages.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.864Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.633Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chat_template.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.345Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.121Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.trl.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.113Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.885Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.preprocess.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.025Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.796Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/kernels.swiglu.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.519Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.298Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/kernels.quantize.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.526Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.305Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.chat_template.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.259Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.033Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.kto.chatml.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.386Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.162Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.grpo.trainer.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.135Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.909Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.mistral_attn_hijack_flash.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.536Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.315Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.datasets.chat.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.873Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.643Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.args.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.950Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.720Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.main.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.915Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.684Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.dpo.trainer.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.125Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.898Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.trl.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.831Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.617Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.passthrough.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.370Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.146Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_tokenizers.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.804Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.572Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.alpaca_chat.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.272Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.047Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/logging_config.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.813Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.581Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/tokenized.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/index.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/pretraining.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/inst_tune.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/qat.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/examples/colab-notebooks/colab-axolotl-example.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.723Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.871Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/FAQS.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.713Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.861Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/installation.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/stepwise_supervised.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/template_free.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset-formats/conversation.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.862Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.dict.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.737Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.521Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.completion.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.312Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.087Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.collators.core.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.042Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.832Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.inference.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.996Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.767Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.freeze.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.667Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.451Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.grpo.sampler.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.147Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.921Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.mixins.rng_state_loader.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.193Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.968Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.utils.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.047Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.819Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.chat.format.shared.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.868Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.638Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.lisa.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.121Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.913Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.collators.mm_chat.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.069Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.860Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.utils.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.149Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.922Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.optimizers.adopt.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.744Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.529Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.base.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.000Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.789Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.user_defined.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.368Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.144Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.btlm_attn_hijack_flash.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.580Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.361Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.quantization.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.773Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.559Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.qat.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.134Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.927Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.builders.base.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.820Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.588Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_cpu.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.612Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.393Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.kd.trainer.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.012Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.802Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.liger.args.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.015Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.805Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.collators.mamba.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.064Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.855Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/loaders.model.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.159Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.932Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schedulers.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.712Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.495Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/kernels.lora.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.498Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.277Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.model_shard_quant.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.656Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.439Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.chat.format.llama3x.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.867Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.636Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.mamba.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.118Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.891Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.enums.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.858Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.645Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.mixtral.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.609Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.390Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/kernels.utils.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.528Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.307Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.training_args.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.841Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.610Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.callbacks.perplexity.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.115Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.907Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.cloud.modal_.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.046Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.817Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.utils.load.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.070Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.841Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/train.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.724Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.495Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.grokfast.optimizer.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.004Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.794Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.samplers.multipack.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.109Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.901Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.metharme.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.329Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.105Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.llama_expand_mask.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.543Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.322Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.data.batch_dataset_fetcher.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.608Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.389Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.lora.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.651Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.433Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/loaders.tokenizer.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.167Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.941Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.chat.format.chatml.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.865Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.635Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.collators.batching.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.061Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.852Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.merge_sharded_fsdp_weights.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.016Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.787Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.llama2_chat.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.306Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.081Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.tokenization.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.645Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.427Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/common.architectures.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.023Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.813Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.datasets.transforms.chat_builder.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.881Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.651Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/core.trainers.base.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.098Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.870Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.lora_kernels.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.571Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.351Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.utils.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.864Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.651Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.llama3.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.355Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.131Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/cli.config.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.977Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.748Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.peft.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.827Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.614Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.user_defined.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.293Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.068Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.zephyr.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.367Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.143Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.multipack.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.538Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.317Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.base.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.226Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.000Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/models.mamba.modeling_mamba.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.040Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.831Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.relora.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.541Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.320Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/common.const.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.024Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.815Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.trainer_fsdp_optim.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.591Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.371Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.distributed.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.731Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.516Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/loaders.constants.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.185Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.959Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.gradient_checkpointing.offload_disk.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.638Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.420Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/datasets.html</loc>
|
||||
<lastmod>2025-08-26T13:33:56.745Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.516Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/monkeypatch.transformers_fa_utils.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.597Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.378Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/loaders.processor.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.168Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.942Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/integrations.spectrum.args.html</loc>
|
||||
<lastmod>2025-08-26T13:33:58.021Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.812Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/loaders.adapter.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.174Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:22.948Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/utils.schemas.model.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.794Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.580Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/api/prompt_strategies.dpo.chatml.html</loc>
|
||||
<lastmod>2025-08-26T13:33:57.365Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:23.141Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/batch_vs_grad.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.862Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/mac.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/nd_parallelism.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/dataset_loading.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/lora_optims.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/unsloth.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.719Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.867Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/config-reference.html</loc>
|
||||
<lastmod>2025-08-26T13:34:11.119Z</lastmod>
|
||||
<lastmod>2025-08-27T08:13:36.599Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/custom_integrations.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.862Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/faq.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.715Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/amd_hpc.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.862Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/multi-node.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/cli.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.714Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.862Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/nccl.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/optimizers.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.866Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/getting-started.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.715Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.863Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/quantize.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.867Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/docs/reward_modelling.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.718Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.867Z</lastmod>
|
||||
</url>
|
||||
<url>
|
||||
<loc>https://docs.axolotl.ai/src/axolotl/integrations/cut_cross_entropy/ACKNOWLEDGEMENTS.html</loc>
|
||||
<lastmod>2025-08-26T13:30:30.739Z</lastmod>
|
||||
<lastmod>2025-08-27T08:10:21.888Z</lastmod>
|
||||
</url>
|
||||
</urlset>
|
||||
|
||||
Reference in New Issue
Block a user