Built site for gh-pages
This commit is contained in:
Quarto GHA Workflow Runner
@@ -75,7 +75,7 @@ pre > code.sourceCode > span > a:first-child::before { text-decoration: underlin
|
||||
<link href="../site_libs/quarto-html/quarto-syntax-highlighting-dark-2fef5ea3f8957b3e4ecc936fc74692ca.css" rel="stylesheet" id="quarto-text-highlighting-styles">
|
||||
<script src="../site_libs/bootstrap/bootstrap.min.js"></script>
|
||||
<link href="../site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet">
|
||||
<link href="../site_libs/bootstrap/bootstrap-7415244d48e501ce6749b46a5d56d2c8.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="dark">
|
||||
<link href="../site_libs/bootstrap/bootstrap-ed9d63b928ec3538d7b05c99c63ac09f.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="dark">
|
||||
<script id="quarto-search-options" type="application/json">{
|
||||
"location": "navbar",
|
||||
"copy-button": false,
|
||||
@@ -1403,308 +1403,312 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<span id="cb1-908"><a href="#cb1-908" aria-hidden="true" tabindex="-1"></a><span class="co"># set to `jinja` or `null` (in which case chat_template is automatically set to</span></span>
|
||||
<span id="cb1-909"><a href="#cb1-909" aria-hidden="true" tabindex="-1"></a><span class="co"># `jinja`). Default is null.</span></span>
|
||||
<span id="cb1-910"><a href="#cb1-910" 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="cb1-911"><a href="#cb1-911" 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="cb1-912"><a href="#cb1-912" aria-hidden="true" tabindex="-1"></a><span class="co"># boundaries between conversation turns. For example: ['/INST', '</s>',</span></span>
|
||||
<span id="cb1-913"><a href="#cb1-913" 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="cb1-914"><a href="#cb1-914" aria-hidden="true" tabindex="-1"></a><span class="co"># useful for templates that use multiple delimiter tokens.</span></span>
|
||||
<span id="cb1-915"><a href="#cb1-915" 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="cb1-916"><a href="#cb1-916" aria-hidden="true" tabindex="-1"></a><span class="co"># Changes the default system message. Currently only supports chatml.</span></span>
|
||||
<span id="cb1-917"><a href="#cb1-917" 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="cb1-918"><a href="#cb1-918" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-919"><a href="#cb1-919" 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="cb1-920"><a href="#cb1-920" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-921"><a href="#cb1-921" 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="cb1-922"><a href="#cb1-922" 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="cb1-923"><a href="#cb1-923" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-924"><a href="#cb1-924" aria-hidden="true" tabindex="-1"></a><span class="co"># Total number of tokens - internal use</span></span>
|
||||
<span id="cb1-925"><a href="#cb1-925" 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="cb1-926"><a href="#cb1-926" 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="cb1-927"><a href="#cb1-927" 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="cb1-928"><a href="#cb1-928" aria-hidden="true" tabindex="-1"></a><span class="co"># trainer will provide recommended values for these values.</span></span>
|
||||
<span id="cb1-929"><a href="#cb1-929" 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="cb1-930"><a href="#cb1-930" 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="cb1-931"><a href="#cb1-931" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-932"><a href="#cb1-932" 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="cb1-933"><a href="#cb1-933" 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="cb1-934"><a href="#cb1-934" 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="cb1-935"><a href="#cb1-935" 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="cb1-936"><a href="#cb1-936" 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="cb1-937"><a href="#cb1-937" 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="cb1-938"><a href="#cb1-938" 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="cb1-939"><a href="#cb1-939" 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="cb1-940"><a href="#cb1-940" 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="cb1-941"><a href="#cb1-941" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-942"><a href="#cb1-942" 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="cb1-943"><a href="#cb1-943" aria-hidden="true" tabindex="-1"></a><span class="co"># plugins or doc below for more details.</span></span>
|
||||
<span id="cb1-944"><a href="#cb1-944" aria-hidden="true" tabindex="-1"></a><span class="co"># https://docs.axolotl.ai/docs/custom_integrations.html</span></span>
|
||||
<span id="cb1-945"><a href="#cb1-945" 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="cb1-946"><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"># This is the huggingface model that contains *.pt, *.safetensors, or *.bin files. This</span></span>
|
||||
<span id="cb1-948"><a href="#cb1-948" aria-hidden="true" tabindex="-1"></a><span class="co"># can also be a relative path to a model on disk</span></span>
|
||||
<span id="cb1-949"><a href="#cb1-949" 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="cb1-950"><a href="#cb1-950" 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="cb1-951"><a href="#cb1-951" 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="cb1-952"><a href="#cb1-952" 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="cb1-953"><a href="#cb1-953" 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="cb1-954"><a href="#cb1-954" 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="cb1-955"><a href="#cb1-955" aria-hidden="true" tabindex="-1"></a><span class="co"># than the one defined in the base model</span></span>
|
||||
<span id="cb1-956"><a href="#cb1-956" 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="cb1-957"><a href="#cb1-957" aria-hidden="true" tabindex="-1"></a><span class="co"># use_fast option for tokenizer loading from_pretrained, default to True</span></span>
|
||||
<span id="cb1-958"><a href="#cb1-958" 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="cb1-959"><a href="#cb1-959" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use the legacy tokenizer setting, defaults to True</span></span>
|
||||
<span id="cb1-960"><a href="#cb1-960" 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="cb1-961"><a href="#cb1-961" 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="cb1-962"><a href="#cb1-962" aria-hidden="true" tabindex="-1"></a><span class="co"># common tokenizer.</span></span>
|
||||
<span id="cb1-963"><a href="#cb1-963" 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="cb1-964"><a href="#cb1-964" aria-hidden="true" tabindex="-1"></a><span class="co"># Corresponding tokenizer for the model AutoTokenizer is a good choice</span></span>
|
||||
<span id="cb1-965"><a href="#cb1-965" 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="cb1-966"><a href="#cb1-966" aria-hidden="true" tabindex="-1"></a><span class="co"># transformers processor class</span></span>
|
||||
<span id="cb1-967"><a href="#cb1-967" 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="cb1-968"><a href="#cb1-968" aria-hidden="true" tabindex="-1"></a><span class="co"># Trust remote code for untrusted source</span></span>
|
||||
<span id="cb1-969"><a href="#cb1-969" 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="cb1-970"><a href="#cb1-970" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-971"><a href="#cb1-971" aria-hidden="true" tabindex="-1"></a><span class="co"># Where to save the full-finetuned model to</span></span>
|
||||
<span id="cb1-972"><a href="#cb1-972" 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="cb1-973"><a href="#cb1-973" aria-hidden="true" tabindex="-1"></a><span class="co"># push checkpoints to hub</span></span>
|
||||
<span id="cb1-974"><a href="#cb1-974" 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="cb1-975"><a href="#cb1-975" aria-hidden="true" tabindex="-1"></a><span class="co"># how to push checkpoints to hub</span></span>
|
||||
<span id="cb1-976"><a href="#cb1-976" 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="cb1-977"><a href="#cb1-977" aria-hidden="true" tabindex="-1"></a><span class="co"># Save model as safetensors (require safetensors package). Default True</span></span>
|
||||
<span id="cb1-978"><a href="#cb1-978" 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="cb1-979"><a href="#cb1-979" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-980"><a href="#cb1-980" 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="cb1-981"><a href="#cb1-981" 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="cb1-982"><a href="#cb1-982" aria-hidden="true" tabindex="-1"></a><span class="co"># Use bitsandbytes 4 bit</span></span>
|
||||
<span id="cb1-983"><a href="#cb1-983" 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="cb1-984"><a href="#cb1-984" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-985"><a href="#cb1-985" 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="cb1-986"><a href="#cb1-986" aria-hidden="true" tabindex="-1"></a><span class="co"># original model</span></span>
|
||||
<span id="cb1-987"><a href="#cb1-987" aria-hidden="true" tabindex="-1"></a><span class="fu">adapter</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-988"><a href="#cb1-988" 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="cb1-989"><a href="#cb1-989" 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="cb1-990"><a href="#cb1-990" 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="cb1-991"><a href="#cb1-991" aria-hidden="true" tabindex="-1"></a><span class="co"># subdirectory `merged` will be created under the `output_dir`.</span></span>
|
||||
<span id="cb1-992"><a href="#cb1-992" 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="cb1-993"><a href="#cb1-993" 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="cb1-994"><a href="#cb1-994" 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="cb1-995"><a href="#cb1-995" 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="cb1-996"><a href="#cb1-996" 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="cb1-997"><a href="#cb1-997" aria-hidden="true" tabindex="-1"></a><span class="co"># If true, will target all linear modules</span></span>
|
||||
<span id="cb1-998"><a href="#cb1-998" 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="cb1-999"><a href="#cb1-999" 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="cb1-1000"><a href="#cb1-1000" 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="cb1-1001"><a href="#cb1-1001" 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="cb1-1002"><a href="#cb1-1002" aria-hidden="true" tabindex="-1"></a><span class="co"># tokens to embeddings, and `lm_head` converts embeddings to token probabilities.</span></span>
|
||||
<span id="cb1-1003"><a href="#cb1-1003" 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="cb1-1004"><a href="#cb1-1004" 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="cb1-1005"><a href="#cb1-1005" aria-hidden="true" tabindex="-1"></a><span class="co"># The layer indices to transform, otherwise, apply to all layers</span></span>
|
||||
<span id="cb1-1006"><a href="#cb1-1006" 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="cb1-1007"><a href="#cb1-1007" 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="cb1-1008"><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="fu">peft</span><span class="kw">:</span><span class="at"> PeftConfig | None</span></span>
|
||||
<span id="cb1-1010"><a href="#cb1-1010" aria-hidden="true" tabindex="-1"></a><span class="co"> # For PeftConfig:</span></span>
|
||||
<span id="cb1-1011"><a href="#cb1-1011" aria-hidden="true" tabindex="-1"></a><span class="co"> # Configuration options for loftq initialization for LoRA</span></span>
|
||||
<span id="cb1-1012"><a href="#cb1-1012" 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="cb1-1013"><a href="#cb1-1013" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LoftQConfig:</span></span>
|
||||
<span id="cb1-1014"><a href="#cb1-1014" aria-hidden="true" tabindex="-1"></a><span class="co"> # typically 4 bits</span></span>
|
||||
<span id="cb1-1015"><a href="#cb1-1015" 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="cb1-1016"><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"># Whether to use DoRA.</span></span>
|
||||
<span id="cb1-1018"><a href="#cb1-1018" 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="cb1-1019"><a href="#cb1-1019" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use RSLoRA.</span></span>
|
||||
<span id="cb1-1020"><a href="#cb1-1020" 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="cb1-1021"><a href="#cb1-1021" aria-hidden="true" tabindex="-1"></a><span class="co"># List of layer indices to replicate.</span></span>
|
||||
<span id="cb1-1022"><a href="#cb1-1022" 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="cb1-1023"><a href="#cb1-1023" 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="cb1-1024"><a href="#cb1-1024" 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="cb1-1025"><a href="#cb1-1025" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1026"><a href="#cb1-1026" 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="cb1-1027"><a href="#cb1-1027" 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="cb1-1028"><a href="#cb1-1028" 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="cb1-1029"><a href="#cb1-1029" 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="cb1-1030"><a href="#cb1-1030" 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="cb1-1031"><a href="#cb1-1031" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether you are training a 4-bit GPTQ quantized model</span></span>
|
||||
<span id="cb1-1032"><a href="#cb1-1032" aria-hidden="true" tabindex="-1"></a><span class="fu">gptq</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1033"><a href="#cb1-1033" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the bnb 4bit quantization configuration</span></span>
|
||||
<span id="cb1-1034"><a href="#cb1-1034" 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="cb1-1035"><a href="#cb1-1035" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1036"><a href="#cb1-1036" 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="cb1-1037"><a href="#cb1-1037" 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="cb1-1038"><a href="#cb1-1038" 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="cb1-1039"><a href="#cb1-1039" 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="cb1-1040"><a href="#cb1-1040" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1041"><a href="#cb1-1041" 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="cb1-1042"><a href="#cb1-1042" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1043"><a href="#cb1-1043" aria-hidden="true" tabindex="-1"></a><span class="co"># Number of steps per ReLoRA restart</span></span>
|
||||
<span id="cb1-1044"><a href="#cb1-1044" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1045"><a href="#cb1-1045" aria-hidden="true" tabindex="-1"></a><span class="co"># Number of per-restart warmup steps</span></span>
|
||||
<span id="cb1-1046"><a href="#cb1-1046" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_warmup_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1047"><a href="#cb1-1047" aria-hidden="true" tabindex="-1"></a><span class="co"># Number of anneal steps for each relora cycle</span></span>
|
||||
<span id="cb1-1048"><a href="#cb1-1048" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_anneal_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1049"><a href="#cb1-1049" aria-hidden="true" tabindex="-1"></a><span class="co"># threshold for optimizer magnitude when pruning</span></span>
|
||||
<span id="cb1-1050"><a href="#cb1-1050" 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="cb1-1051"><a href="#cb1-1051" 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="cb1-1052"><a href="#cb1-1052" aria-hidden="true" tabindex="-1"></a><span class="co"># savings</span></span>
|
||||
<span id="cb1-1053"><a href="#cb1-1053" 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="cb1-1054"><a href="#cb1-1054" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1055"><a href="#cb1-1055" 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="cb1-1056"><a href="#cb1-1056" aria-hidden="true" tabindex="-1"></a><span class="co"># accumulated for the given number of steps.</span></span>
|
||||
<span id="cb1-1057"><a href="#cb1-1057" 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="cb1-1058"><a href="#cb1-1058" 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="cb1-1059"><a href="#cb1-1059" 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="cb1-1060"><a href="#cb1-1060" 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="cb1-1061"><a href="#cb1-1061" aria-hidden="true" tabindex="-1"></a><span class="co"># Total batch size, we do not recommended setting this manually</span></span>
|
||||
<span id="cb1-1062"><a href="#cb1-1062" 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="cb1-1063"><a href="#cb1-1063" 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="cb1-1064"><a href="#cb1-1064" 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="cb1-1065"><a href="#cb1-1065" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1066"><a href="#cb1-1066" 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="cb1-1067"><a href="#cb1-1067" aria-hidden="true" tabindex="-1"></a><span class="co"># Trainer</span></span>
|
||||
<span id="cb1-1068"><a href="#cb1-1068" 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="cb1-911"><a href="#cb1-911" 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="cb1-912"><a href="#cb1-912" 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="cb1-913"><a href="#cb1-913" aria-hidden="true" tabindex="-1"></a><span class="co"># to the chat template.</span></span>
|
||||
<span id="cb1-914"><a href="#cb1-914" 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="cb1-915"><a href="#cb1-915" 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="cb1-916"><a href="#cb1-916" aria-hidden="true" tabindex="-1"></a><span class="co"># boundaries between conversation turns. For example: ['/INST', '</s>',</span></span>
|
||||
<span id="cb1-917"><a href="#cb1-917" 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="cb1-918"><a href="#cb1-918" aria-hidden="true" tabindex="-1"></a><span class="co"># useful for templates that use multiple delimiter tokens.</span></span>
|
||||
<span id="cb1-919"><a href="#cb1-919" 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="cb1-920"><a href="#cb1-920" aria-hidden="true" tabindex="-1"></a><span class="co"># Changes the default system message. Currently only supports chatml.</span></span>
|
||||
<span id="cb1-921"><a href="#cb1-921" 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="cb1-922"><a href="#cb1-922" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-923"><a href="#cb1-923" 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="cb1-924"><a href="#cb1-924" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-925"><a href="#cb1-925" 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="cb1-926"><a href="#cb1-926" 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="cb1-927"><a href="#cb1-927" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-928"><a href="#cb1-928" aria-hidden="true" tabindex="-1"></a><span class="co"># Total number of tokens - internal use</span></span>
|
||||
<span id="cb1-929"><a href="#cb1-929" 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="cb1-930"><a href="#cb1-930" 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="cb1-931"><a href="#cb1-931" 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="cb1-932"><a href="#cb1-932" aria-hidden="true" tabindex="-1"></a><span class="co"># trainer will provide recommended values for these values.</span></span>
|
||||
<span id="cb1-933"><a href="#cb1-933" 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="cb1-934"><a href="#cb1-934" 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="cb1-935"><a href="#cb1-935" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-936"><a href="#cb1-936" 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="cb1-937"><a href="#cb1-937" 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="cb1-938"><a href="#cb1-938" 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="cb1-939"><a href="#cb1-939" 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="cb1-940"><a href="#cb1-940" 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="cb1-941"><a href="#cb1-941" 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="cb1-942"><a href="#cb1-942" 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="cb1-943"><a href="#cb1-943" 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="cb1-944"><a href="#cb1-944" 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="cb1-945"><a href="#cb1-945" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-946"><a href="#cb1-946" 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="cb1-947"><a href="#cb1-947" aria-hidden="true" tabindex="-1"></a><span class="co"># plugins or doc below for more details.</span></span>
|
||||
<span id="cb1-948"><a href="#cb1-948" aria-hidden="true" tabindex="-1"></a><span class="co"># https://docs.axolotl.ai/docs/custom_integrations.html</span></span>
|
||||
<span id="cb1-949"><a href="#cb1-949" 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="cb1-950"><a href="#cb1-950" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-951"><a href="#cb1-951" 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="cb1-952"><a href="#cb1-952" aria-hidden="true" tabindex="-1"></a><span class="co"># can also be a relative path to a model on disk</span></span>
|
||||
<span id="cb1-953"><a href="#cb1-953" 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="cb1-954"><a href="#cb1-954" 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="cb1-955"><a href="#cb1-955" 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="cb1-956"><a href="#cb1-956" 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="cb1-957"><a href="#cb1-957" 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="cb1-958"><a href="#cb1-958" 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="cb1-959"><a href="#cb1-959" aria-hidden="true" tabindex="-1"></a><span class="co"># than the one defined in the base model</span></span>
|
||||
<span id="cb1-960"><a href="#cb1-960" 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="cb1-961"><a href="#cb1-961" aria-hidden="true" tabindex="-1"></a><span class="co"># use_fast option for tokenizer loading from_pretrained, default to True</span></span>
|
||||
<span id="cb1-962"><a href="#cb1-962" 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="cb1-963"><a href="#cb1-963" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use the legacy tokenizer setting, defaults to True</span></span>
|
||||
<span id="cb1-964"><a href="#cb1-964" 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="cb1-965"><a href="#cb1-965" 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="cb1-966"><a href="#cb1-966" aria-hidden="true" tabindex="-1"></a><span class="co"># common tokenizer.</span></span>
|
||||
<span id="cb1-967"><a href="#cb1-967" 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="cb1-968"><a href="#cb1-968" aria-hidden="true" tabindex="-1"></a><span class="co"># Corresponding tokenizer for the model AutoTokenizer is a good choice</span></span>
|
||||
<span id="cb1-969"><a href="#cb1-969" 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="cb1-970"><a href="#cb1-970" aria-hidden="true" tabindex="-1"></a><span class="co"># transformers processor class</span></span>
|
||||
<span id="cb1-971"><a href="#cb1-971" 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="cb1-972"><a href="#cb1-972" aria-hidden="true" tabindex="-1"></a><span class="co"># Trust remote code for untrusted source</span></span>
|
||||
<span id="cb1-973"><a href="#cb1-973" 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="cb1-974"><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"># Where to save the full-finetuned model to</span></span>
|
||||
<span id="cb1-976"><a href="#cb1-976" 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="cb1-977"><a href="#cb1-977" aria-hidden="true" tabindex="-1"></a><span class="co"># push checkpoints to hub</span></span>
|
||||
<span id="cb1-978"><a href="#cb1-978" 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="cb1-979"><a href="#cb1-979" aria-hidden="true" tabindex="-1"></a><span class="co"># how to push checkpoints to hub</span></span>
|
||||
<span id="cb1-980"><a href="#cb1-980" 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="cb1-981"><a href="#cb1-981" aria-hidden="true" tabindex="-1"></a><span class="co"># Save model as safetensors (require safetensors package). Default True</span></span>
|
||||
<span id="cb1-982"><a href="#cb1-982" 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="cb1-983"><a href="#cb1-983" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-984"><a href="#cb1-984" 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="cb1-985"><a href="#cb1-985" 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="cb1-986"><a href="#cb1-986" aria-hidden="true" tabindex="-1"></a><span class="co"># Use bitsandbytes 4 bit</span></span>
|
||||
<span id="cb1-987"><a href="#cb1-987" 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="cb1-988"><a href="#cb1-988" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-989"><a href="#cb1-989" 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="cb1-990"><a href="#cb1-990" aria-hidden="true" tabindex="-1"></a><span class="co"># original model</span></span>
|
||||
<span id="cb1-991"><a href="#cb1-991" aria-hidden="true" tabindex="-1"></a><span class="fu">adapter</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-992"><a href="#cb1-992" 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="cb1-993"><a href="#cb1-993" 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="cb1-994"><a href="#cb1-994" 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="cb1-995"><a href="#cb1-995" aria-hidden="true" tabindex="-1"></a><span class="co"># subdirectory `merged` will be created under the `output_dir`.</span></span>
|
||||
<span id="cb1-996"><a href="#cb1-996" 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="cb1-997"><a href="#cb1-997" 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="cb1-998"><a href="#cb1-998" 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="cb1-999"><a href="#cb1-999" 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="cb1-1000"><a href="#cb1-1000" 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="cb1-1001"><a href="#cb1-1001" aria-hidden="true" tabindex="-1"></a><span class="co"># If true, will target all linear modules</span></span>
|
||||
<span id="cb1-1002"><a href="#cb1-1002" 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="cb1-1003"><a href="#cb1-1003" 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="cb1-1004"><a href="#cb1-1004" 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="cb1-1005"><a href="#cb1-1005" 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="cb1-1006"><a href="#cb1-1006" aria-hidden="true" tabindex="-1"></a><span class="co"># tokens to embeddings, and `lm_head` converts embeddings to token probabilities.</span></span>
|
||||
<span id="cb1-1007"><a href="#cb1-1007" 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="cb1-1008"><a href="#cb1-1008" 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="cb1-1009"><a href="#cb1-1009" aria-hidden="true" tabindex="-1"></a><span class="co"># The layer indices to transform, otherwise, apply to all layers</span></span>
|
||||
<span id="cb1-1010"><a href="#cb1-1010" 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="cb1-1011"><a href="#cb1-1011" 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="cb1-1012"><a href="#cb1-1012" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1013"><a href="#cb1-1013" aria-hidden="true" tabindex="-1"></a><span class="fu">peft</span><span class="kw">:</span><span class="at"> PeftConfig | None</span></span>
|
||||
<span id="cb1-1014"><a href="#cb1-1014" aria-hidden="true" tabindex="-1"></a><span class="co"> # For PeftConfig:</span></span>
|
||||
<span id="cb1-1015"><a href="#cb1-1015" aria-hidden="true" tabindex="-1"></a><span class="co"> # Configuration options for loftq initialization for LoRA</span></span>
|
||||
<span id="cb1-1016"><a href="#cb1-1016" 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="cb1-1017"><a href="#cb1-1017" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LoftQConfig:</span></span>
|
||||
<span id="cb1-1018"><a href="#cb1-1018" aria-hidden="true" tabindex="-1"></a><span class="co"> # typically 4 bits</span></span>
|
||||
<span id="cb1-1019"><a href="#cb1-1019" 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="cb1-1020"><a href="#cb1-1020" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1021"><a href="#cb1-1021" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use DoRA.</span></span>
|
||||
<span id="cb1-1022"><a href="#cb1-1022" 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="cb1-1023"><a href="#cb1-1023" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use RSLoRA.</span></span>
|
||||
<span id="cb1-1024"><a href="#cb1-1024" 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="cb1-1025"><a href="#cb1-1025" aria-hidden="true" tabindex="-1"></a><span class="co"># List of layer indices to replicate.</span></span>
|
||||
<span id="cb1-1026"><a href="#cb1-1026" 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="cb1-1027"><a href="#cb1-1027" 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="cb1-1028"><a href="#cb1-1028" 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="cb1-1029"><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"># load qlora model in sharded format for FSDP using answer.ai technique.</span></span>
|
||||
<span id="cb1-1031"><a href="#cb1-1031" 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="cb1-1032"><a href="#cb1-1032" 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="cb1-1033"><a href="#cb1-1033" 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="cb1-1034"><a href="#cb1-1034" 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="cb1-1035"><a href="#cb1-1035" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether you are training a 4-bit GPTQ quantized model</span></span>
|
||||
<span id="cb1-1036"><a href="#cb1-1036" aria-hidden="true" tabindex="-1"></a><span class="fu">gptq</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1037"><a href="#cb1-1037" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the bnb 4bit quantization configuration</span></span>
|
||||
<span id="cb1-1038"><a href="#cb1-1038" 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="cb1-1039"><a href="#cb1-1039" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1040"><a href="#cb1-1040" 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="cb1-1041"><a href="#cb1-1041" 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="cb1-1042"><a href="#cb1-1042" 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="cb1-1043"><a href="#cb1-1043" 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="cb1-1044"><a href="#cb1-1044" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1045"><a href="#cb1-1045" 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="cb1-1046"><a href="#cb1-1046" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1047"><a href="#cb1-1047" aria-hidden="true" tabindex="-1"></a><span class="co"># Number of steps per ReLoRA restart</span></span>
|
||||
<span id="cb1-1048"><a href="#cb1-1048" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1049"><a href="#cb1-1049" aria-hidden="true" tabindex="-1"></a><span class="co"># Number of per-restart warmup steps</span></span>
|
||||
<span id="cb1-1050"><a href="#cb1-1050" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_warmup_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1051"><a href="#cb1-1051" aria-hidden="true" tabindex="-1"></a><span class="co"># Number of anneal steps for each relora cycle</span></span>
|
||||
<span id="cb1-1052"><a href="#cb1-1052" aria-hidden="true" tabindex="-1"></a><span class="fu">relora_anneal_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1053"><a href="#cb1-1053" aria-hidden="true" tabindex="-1"></a><span class="co"># threshold for optimizer magnitude when pruning</span></span>
|
||||
<span id="cb1-1054"><a href="#cb1-1054" 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="cb1-1055"><a href="#cb1-1055" 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="cb1-1056"><a href="#cb1-1056" aria-hidden="true" tabindex="-1"></a><span class="co"># savings</span></span>
|
||||
<span id="cb1-1057"><a href="#cb1-1057" 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="cb1-1058"><a href="#cb1-1058" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1059"><a href="#cb1-1059" 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="cb1-1060"><a href="#cb1-1060" aria-hidden="true" tabindex="-1"></a><span class="co"># accumulated for the given number of steps.</span></span>
|
||||
<span id="cb1-1061"><a href="#cb1-1061" 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="cb1-1062"><a href="#cb1-1062" 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="cb1-1063"><a href="#cb1-1063" 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="cb1-1064"><a href="#cb1-1064" 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="cb1-1065"><a href="#cb1-1065" aria-hidden="true" tabindex="-1"></a><span class="co"># Total batch size, we do not recommended setting this manually</span></span>
|
||||
<span id="cb1-1066"><a href="#cb1-1066" 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="cb1-1067"><a href="#cb1-1067" 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="cb1-1068"><a href="#cb1-1068" 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="cb1-1069"><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"># Whether to mask out or include the human's prompt from the training labels</span></span>
|
||||
<span id="cb1-1071"><a href="#cb1-1071" 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="cb1-1072"><a href="#cb1-1072" 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="cb1-1073"><a href="#cb1-1073" 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="cb1-1074"><a href="#cb1-1074" aria-hidden="true" tabindex="-1"></a><span class="co"># pattern with this enabled.</span></span>
|
||||
<span id="cb1-1075"><a href="#cb1-1075" 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="cb1-1076"><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="fu">learning_rate</span><span class="kw">:</span><span class="at"> str | float (required)</span></span>
|
||||
<span id="cb1-1078"><a href="#cb1-1078" 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="cb1-1079"><a href="#cb1-1079" 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="cb1-1080"><a href="#cb1-1080" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify weight decay</span></span>
|
||||
<span id="cb1-1081"><a href="#cb1-1081" 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="cb1-1082"><a href="#cb1-1082" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify optimizer</span></span>
|
||||
<span id="cb1-1083"><a href="#cb1-1083" 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="cb1-1084"><a href="#cb1-1084" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary of arguments to pass to the optimizer</span></span>
|
||||
<span id="cb1-1085"><a href="#cb1-1085" 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="cb1-1086"><a href="#cb1-1086" 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="cb1-1087"><a href="#cb1-1087" aria-hidden="true" tabindex="-1"></a><span class="co"># right now this is used only for GaLore algorithm</span></span>
|
||||
<span id="cb1-1088"><a href="#cb1-1088" 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="cb1-1089"><a href="#cb1-1089" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
|
||||
<span id="cb1-1090"><a href="#cb1-1090" 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="cb1-1091"><a href="#cb1-1091" 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="cb1-1092"><a href="#cb1-1092" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify a scheduler and kwargs to use with the optimizer</span></span>
|
||||
<span id="cb1-1093"><a href="#cb1-1093" 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="cb1-1094"><a href="#cb1-1094" 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="cb1-1095"><a href="#cb1-1095" 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="cb1-1096"><a href="#cb1-1096" aria-hidden="true" tabindex="-1"></a><span class="co"># peak lr</span></span>
|
||||
<span id="cb1-1097"><a href="#cb1-1097" 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="cb1-1098"><a href="#cb1-1098" 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="cb1-1099"><a href="#cb1-1099" aria-hidden="true" tabindex="-1"></a><span class="co"># start cosine_min_lr at 80% of training step</span></span>
|
||||
<span id="cb1-1100"><a href="#cb1-1100" 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="cb1-1101"><a href="#cb1-1101" aria-hidden="true" tabindex="-1"></a><span class="co"># Learning rate div factor</span></span>
|
||||
<span id="cb1-1102"><a href="#cb1-1102" 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="cb1-1103"><a href="#cb1-1103" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1104"><a href="#cb1-1104" 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="cb1-1105"><a href="#cb1-1105" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LrGroup:</span></span>
|
||||
<span id="cb1-1106"><a href="#cb1-1106" 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="cb1-1107"><a href="#cb1-1107" 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="cb1-1108"><a href="#cb1-1108" 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="cb1-1109"><a href="#cb1-1109" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1110"><a href="#cb1-1110" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1111"><a href="#cb1-1111" 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="cb1-1112"><a href="#cb1-1112" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1113"><a href="#cb1-1113" 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="cb1-1070"><a href="#cb1-1070" 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="cb1-1071"><a href="#cb1-1071" aria-hidden="true" tabindex="-1"></a><span class="co"># Trainer</span></span>
|
||||
<span id="cb1-1072"><a href="#cb1-1072" 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="cb1-1073"><a href="#cb1-1073" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1074"><a href="#cb1-1074" 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="cb1-1075"><a href="#cb1-1075" 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="cb1-1076"><a href="#cb1-1076" 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="cb1-1077"><a href="#cb1-1077" 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="cb1-1078"><a href="#cb1-1078" aria-hidden="true" tabindex="-1"></a><span class="co"># pattern with this enabled.</span></span>
|
||||
<span id="cb1-1079"><a href="#cb1-1079" 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="cb1-1080"><a href="#cb1-1080" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1081"><a href="#cb1-1081" 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="cb1-1082"><a href="#cb1-1082" 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="cb1-1083"><a href="#cb1-1083" 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="cb1-1084"><a href="#cb1-1084" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify weight decay</span></span>
|
||||
<span id="cb1-1085"><a href="#cb1-1085" 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="cb1-1086"><a href="#cb1-1086" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify optimizer</span></span>
|
||||
<span id="cb1-1087"><a href="#cb1-1087" 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="cb1-1088"><a href="#cb1-1088" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary of arguments to pass to the optimizer</span></span>
|
||||
<span id="cb1-1089"><a href="#cb1-1089" 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="cb1-1090"><a href="#cb1-1090" 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="cb1-1091"><a href="#cb1-1091" aria-hidden="true" tabindex="-1"></a><span class="co"># right now this is used only for GaLore algorithm</span></span>
|
||||
<span id="cb1-1092"><a href="#cb1-1092" 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="cb1-1093"><a href="#cb1-1093" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
|
||||
<span id="cb1-1094"><a href="#cb1-1094" 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="cb1-1095"><a href="#cb1-1095" 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="cb1-1096"><a href="#cb1-1096" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify a scheduler and kwargs to use with the optimizer</span></span>
|
||||
<span id="cb1-1097"><a href="#cb1-1097" 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="cb1-1098"><a href="#cb1-1098" 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="cb1-1099"><a href="#cb1-1099" 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="cb1-1100"><a href="#cb1-1100" aria-hidden="true" tabindex="-1"></a><span class="co"># peak lr</span></span>
|
||||
<span id="cb1-1101"><a href="#cb1-1101" 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="cb1-1102"><a href="#cb1-1102" 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="cb1-1103"><a href="#cb1-1103" aria-hidden="true" tabindex="-1"></a><span class="co"># start cosine_min_lr at 80% of training step</span></span>
|
||||
<span id="cb1-1104"><a href="#cb1-1104" 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="cb1-1105"><a href="#cb1-1105" aria-hidden="true" tabindex="-1"></a><span class="co"># Learning rate div factor</span></span>
|
||||
<span id="cb1-1106"><a href="#cb1-1106" 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="cb1-1107"><a href="#cb1-1107" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1108"><a href="#cb1-1108" 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="cb1-1109"><a href="#cb1-1109" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LrGroup:</span></span>
|
||||
<span id="cb1-1110"><a href="#cb1-1110" 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="cb1-1111"><a href="#cb1-1111" 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="cb1-1112"><a href="#cb1-1112" 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="cb1-1113"><a href="#cb1-1113" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1114"><a href="#cb1-1114" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1115"><a href="#cb1-1115" 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="cb1-1116"><a href="#cb1-1116" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1117"><a href="#cb1-1117" 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="cb1-1118"><a href="#cb1-1118" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1119"><a href="#cb1-1119" 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="cb1-1120"><a href="#cb1-1120" aria-hidden="true" tabindex="-1"></a><span class="co"># Gradient clipping max norm</span></span>
|
||||
<span id="cb1-1121"><a href="#cb1-1121" 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="cb1-1122"><a href="#cb1-1122" 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="cb1-1123"><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="fu">use_wandb</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1125"><a href="#cb1-1125" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your wandb run</span></span>
|
||||
<span id="cb1-1126"><a href="#cb1-1126" 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="cb1-1127"><a href="#cb1-1127" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the ID of your wandb run</span></span>
|
||||
<span id="cb1-1128"><a href="#cb1-1128" 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="cb1-1129"><a href="#cb1-1129" 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="cb1-1130"><a href="#cb1-1130" aria-hidden="true" tabindex="-1"></a><span class="co"># off wandb</span></span>
|
||||
<span id="cb1-1131"><a href="#cb1-1131" 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="cb1-1132"><a href="#cb1-1132" aria-hidden="true" tabindex="-1"></a><span class="co"># Your wandb project name</span></span>
|
||||
<span id="cb1-1133"><a href="#cb1-1133" 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="cb1-1134"><a href="#cb1-1134" aria-hidden="true" tabindex="-1"></a><span class="co"># A wandb Team name if using a Team</span></span>
|
||||
<span id="cb1-1135"><a href="#cb1-1135" 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="cb1-1136"><a href="#cb1-1136" 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="cb1-1137"><a href="#cb1-1137" 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="cb1-1138"><a href="#cb1-1138" aria-hidden="true" tabindex="-1"></a><span class="co"># at the end of training</span></span>
|
||||
<span id="cb1-1139"><a href="#cb1-1139" 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="cb1-1140"><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="fu">use_mlflow</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 class="co"># URI to mlflow</span></span>
|
||||
<span id="cb1-1143"><a href="#cb1-1143" 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="cb1-1144"><a href="#cb1-1144" aria-hidden="true" tabindex="-1"></a><span class="co"># Your experiment name</span></span>
|
||||
<span id="cb1-1145"><a href="#cb1-1145" 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="cb1-1146"><a href="#cb1-1146" aria-hidden="true" tabindex="-1"></a><span class="co"># Your run name</span></span>
|
||||
<span id="cb1-1147"><a href="#cb1-1147" 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="cb1-1148"><a href="#cb1-1148" 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="cb1-1149"><a href="#cb1-1149" 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="cb1-1150"><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"># Enable or disable Comet integration.</span></span>
|
||||
<span id="cb1-1152"><a href="#cb1-1152" 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="cb1-1153"><a href="#cb1-1153" aria-hidden="true" tabindex="-1"></a><span class="co"># API key for Comet. Recommended to set via `comet login`.</span></span>
|
||||
<span id="cb1-1154"><a href="#cb1-1154" 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="cb1-1155"><a href="#cb1-1155" aria-hidden="true" tabindex="-1"></a><span class="co"># Workspace name in Comet. Defaults to the user's default workspace.</span></span>
|
||||
<span id="cb1-1156"><a href="#cb1-1156" 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="cb1-1157"><a href="#cb1-1157" aria-hidden="true" tabindex="-1"></a><span class="co"># Project name in Comet. Defaults to Uncategorized.</span></span>
|
||||
<span id="cb1-1158"><a href="#cb1-1158" 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="cb1-1159"><a href="#cb1-1159" 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="cb1-1160"><a href="#cb1-1160" aria-hidden="true" tabindex="-1"></a><span class="co"># control the key of new experiments. Default to a random key.</span></span>
|
||||
<span id="cb1-1161"><a href="#cb1-1161" 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="cb1-1162"><a href="#cb1-1162" 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="cb1-1163"><a href="#cb1-1163" aria-hidden="true" tabindex="-1"></a><span class="co"># ("get_or_create") auto-selects based on configuration.</span></span>
|
||||
<span id="cb1-1164"><a href="#cb1-1164" 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="cb1-1165"><a href="#cb1-1165" 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="cb1-1166"><a href="#cb1-1166" aria-hidden="true" tabindex="-1"></a><span class="co"># True.</span></span>
|
||||
<span id="cb1-1167"><a href="#cb1-1167" 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="cb1-1168"><a href="#cb1-1168" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary for additional configuration settings, see the doc for more details.</span></span>
|
||||
<span id="cb1-1169"><a href="#cb1-1169" 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="cb1-1170"><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"># the number of activate layers in LISA</span></span>
|
||||
<span id="cb1-1172"><a href="#cb1-1172" 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="cb1-1173"><a href="#cb1-1173" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to switch layers in LISA</span></span>
|
||||
<span id="cb1-1174"><a href="#cb1-1174" 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="cb1-1175"><a href="#cb1-1175" aria-hidden="true" tabindex="-1"></a><span class="co"># path under the model to access the layers</span></span>
|
||||
<span id="cb1-1176"><a href="#cb1-1176" 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="cb1-1177"><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">gradio_title</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1179"><a href="#cb1-1179" 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="cb1-1180"><a href="#cb1-1180" 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="cb1-1181"><a href="#cb1-1181" 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="cb1-1182"><a href="#cb1-1182" 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="cb1-1183"><a href="#cb1-1183" 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="cb1-1184"><a href="#cb1-1184" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1185"><a href="#cb1-1185" 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="cb1-1186"><a href="#cb1-1186" 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="cb1-1187"><a href="#cb1-1187" 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="cb1-1188"><a href="#cb1-1188" 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="cb1-1189"><a href="#cb1-1189" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1190"><a href="#cb1-1190" 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="cb1-1191"><a href="#cb1-1191" 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="cb1-1192"><a href="#cb1-1192" aria-hidden="true" tabindex="-1"></a><span class="co"># preprocessor.size, otherwise, images won't be resized.</span></span>
|
||||
<span id="cb1-1193"><a href="#cb1-1193" 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="cb1-1194"><a href="#cb1-1194" 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="cb1-1195"><a href="#cb1-1195" aria-hidden="true" tabindex="-1"></a><span class="co"># to PIL.Image.Resampling for more details.</span></span>
|
||||
<span id="cb1-1196"><a href="#cb1-1196" 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="cb1-1197"><a href="#cb1-1197" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1198"><a href="#cb1-1198" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the base model configuration</span></span>
|
||||
<span id="cb1-1199"><a href="#cb1-1199" 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="cb1-1200"><a href="#cb1-1200" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides the base model loading from_pretrained</span></span>
|
||||
<span id="cb1-1201"><a href="#cb1-1201" 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="cb1-1202"><a href="#cb1-1202" 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="cb1-1203"><a href="#cb1-1203" aria-hidden="true" tabindex="-1"></a><span class="co"># choice too</span></span>
|
||||
<span id="cb1-1204"><a href="#cb1-1204" 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="cb1-1205"><a href="#cb1-1205" 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="cb1-1206"><a href="#cb1-1206" 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="cb1-1207"><a href="#cb1-1207" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1208"><a href="#cb1-1208" 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="cb1-1209"><a href="#cb1-1209" 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="cb1-1210"><a href="#cb1-1210" 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="cb1-1211"><a href="#cb1-1211" 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="cb1-1212"><a href="#cb1-1212" 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="cb1-1115"><a href="#cb1-1115" 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="cb1-1116"><a href="#cb1-1116" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1117"><a href="#cb1-1117" 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="cb1-1118"><a href="#cb1-1118" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1119"><a href="#cb1-1119" 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="cb1-1120"><a href="#cb1-1120" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1121"><a href="#cb1-1121" 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="cb1-1122"><a href="#cb1-1122" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1123"><a href="#cb1-1123" 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="cb1-1124"><a href="#cb1-1124" aria-hidden="true" tabindex="-1"></a><span class="co"># Gradient clipping max norm</span></span>
|
||||
<span id="cb1-1125"><a href="#cb1-1125" 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="cb1-1126"><a href="#cb1-1126" 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="cb1-1127"><a href="#cb1-1127" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1128"><a href="#cb1-1128" 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="cb1-1129"><a href="#cb1-1129" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your wandb run</span></span>
|
||||
<span id="cb1-1130"><a href="#cb1-1130" 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="cb1-1131"><a href="#cb1-1131" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the ID of your wandb run</span></span>
|
||||
<span id="cb1-1132"><a href="#cb1-1132" 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="cb1-1133"><a href="#cb1-1133" 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="cb1-1134"><a href="#cb1-1134" aria-hidden="true" tabindex="-1"></a><span class="co"># off wandb</span></span>
|
||||
<span id="cb1-1135"><a href="#cb1-1135" 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="cb1-1136"><a href="#cb1-1136" aria-hidden="true" tabindex="-1"></a><span class="co"># Your wandb project name</span></span>
|
||||
<span id="cb1-1137"><a href="#cb1-1137" 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="cb1-1138"><a href="#cb1-1138" aria-hidden="true" tabindex="-1"></a><span class="co"># A wandb Team name if using a Team</span></span>
|
||||
<span id="cb1-1139"><a href="#cb1-1139" 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="cb1-1140"><a href="#cb1-1140" 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="cb1-1141"><a href="#cb1-1141" 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="cb1-1142"><a href="#cb1-1142" aria-hidden="true" tabindex="-1"></a><span class="co"># at the end of training</span></span>
|
||||
<span id="cb1-1143"><a href="#cb1-1143" 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="cb1-1144"><a href="#cb1-1144" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1145"><a href="#cb1-1145" 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="cb1-1146"><a href="#cb1-1146" aria-hidden="true" tabindex="-1"></a><span class="co"># URI to mlflow</span></span>
|
||||
<span id="cb1-1147"><a href="#cb1-1147" 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="cb1-1148"><a href="#cb1-1148" aria-hidden="true" tabindex="-1"></a><span class="co"># Your experiment name</span></span>
|
||||
<span id="cb1-1149"><a href="#cb1-1149" 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="cb1-1150"><a href="#cb1-1150" aria-hidden="true" tabindex="-1"></a><span class="co"># Your run name</span></span>
|
||||
<span id="cb1-1151"><a href="#cb1-1151" 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="cb1-1152"><a href="#cb1-1152" 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="cb1-1153"><a href="#cb1-1153" 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="cb1-1154"><a href="#cb1-1154" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1155"><a href="#cb1-1155" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable or disable Comet integration.</span></span>
|
||||
<span id="cb1-1156"><a href="#cb1-1156" 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="cb1-1157"><a href="#cb1-1157" aria-hidden="true" tabindex="-1"></a><span class="co"># API key for Comet. Recommended to set via `comet login`.</span></span>
|
||||
<span id="cb1-1158"><a href="#cb1-1158" 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="cb1-1159"><a href="#cb1-1159" aria-hidden="true" tabindex="-1"></a><span class="co"># Workspace name in Comet. Defaults to the user's default workspace.</span></span>
|
||||
<span id="cb1-1160"><a href="#cb1-1160" 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="cb1-1161"><a href="#cb1-1161" aria-hidden="true" tabindex="-1"></a><span class="co"># Project name in Comet. Defaults to Uncategorized.</span></span>
|
||||
<span id="cb1-1162"><a href="#cb1-1162" 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="cb1-1163"><a href="#cb1-1163" 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="cb1-1164"><a href="#cb1-1164" aria-hidden="true" tabindex="-1"></a><span class="co"># control the key of new experiments. Default to a random key.</span></span>
|
||||
<span id="cb1-1165"><a href="#cb1-1165" 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="cb1-1166"><a href="#cb1-1166" 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="cb1-1167"><a href="#cb1-1167" aria-hidden="true" tabindex="-1"></a><span class="co"># ("get_or_create") auto-selects based on configuration.</span></span>
|
||||
<span id="cb1-1168"><a href="#cb1-1168" 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="cb1-1169"><a href="#cb1-1169" 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="cb1-1170"><a href="#cb1-1170" aria-hidden="true" tabindex="-1"></a><span class="co"># True.</span></span>
|
||||
<span id="cb1-1171"><a href="#cb1-1171" 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="cb1-1172"><a href="#cb1-1172" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary for additional configuration settings, see the doc for more details.</span></span>
|
||||
<span id="cb1-1173"><a href="#cb1-1173" 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="cb1-1174"><a href="#cb1-1174" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1175"><a href="#cb1-1175" aria-hidden="true" tabindex="-1"></a><span class="co"># the number of activate layers in LISA</span></span>
|
||||
<span id="cb1-1176"><a href="#cb1-1176" 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="cb1-1177"><a href="#cb1-1177" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to switch layers in LISA</span></span>
|
||||
<span id="cb1-1178"><a href="#cb1-1178" 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="cb1-1179"><a href="#cb1-1179" aria-hidden="true" tabindex="-1"></a><span class="co"># path under the model to access the layers</span></span>
|
||||
<span id="cb1-1180"><a href="#cb1-1180" 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="cb1-1181"><a href="#cb1-1181" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1182"><a href="#cb1-1182" 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="cb1-1183"><a href="#cb1-1183" 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="cb1-1184"><a href="#cb1-1184" 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="cb1-1185"><a href="#cb1-1185" 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="cb1-1186"><a href="#cb1-1186" 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="cb1-1187"><a href="#cb1-1187" 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="cb1-1188"><a href="#cb1-1188" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1189"><a href="#cb1-1189" 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="cb1-1190"><a href="#cb1-1190" 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="cb1-1191"><a href="#cb1-1191" 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="cb1-1192"><a href="#cb1-1192" 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="cb1-1193"><a href="#cb1-1193" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1194"><a href="#cb1-1194" 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="cb1-1195"><a href="#cb1-1195" 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="cb1-1196"><a href="#cb1-1196" aria-hidden="true" tabindex="-1"></a><span class="co"># preprocessor.size, otherwise, images won't be resized.</span></span>
|
||||
<span id="cb1-1197"><a href="#cb1-1197" 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="cb1-1198"><a href="#cb1-1198" 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="cb1-1199"><a href="#cb1-1199" aria-hidden="true" tabindex="-1"></a><span class="co"># to PIL.Image.Resampling for more details.</span></span>
|
||||
<span id="cb1-1200"><a href="#cb1-1200" 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="cb1-1201"><a href="#cb1-1201" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1202"><a href="#cb1-1202" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the base model configuration</span></span>
|
||||
<span id="cb1-1203"><a href="#cb1-1203" 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="cb1-1204"><a href="#cb1-1204" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides the base model loading from_pretrained</span></span>
|
||||
<span id="cb1-1205"><a href="#cb1-1205" 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="cb1-1206"><a href="#cb1-1206" 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="cb1-1207"><a href="#cb1-1207" aria-hidden="true" tabindex="-1"></a><span class="co"># choice too</span></span>
|
||||
<span id="cb1-1208"><a href="#cb1-1208" 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="cb1-1209"><a href="#cb1-1209" 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="cb1-1210"><a href="#cb1-1210" 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="cb1-1211"><a href="#cb1-1211" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1212"><a href="#cb1-1212" 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="cb1-1213"><a href="#cb1-1213" 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="cb1-1214"><a href="#cb1-1214" 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="cb1-1215"><a href="#cb1-1215" 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="cb1-1216"><a href="#cb1-1216" 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>
|
||||
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user