Built site for gh-pages
This commit is contained in:
Quarto GHA Workflow Runner
@@ -1879,321 +1879,323 @@ gtag('config', 'G-9KYCVJBNMQ', { 'anonymize_ip': true});
|
||||
<span id="cb1-1109"><a href="#cb1-1109" 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="cb1-1110"><a href="#cb1-1110" 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="cb1-1111"><a href="#cb1-1111" 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="cb1-1112"><a href="#cb1-1112" 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="cb1-1113"><a href="#cb1-1113" 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="cb1-1114"><a href="#cb1-1114" aria-hidden="true" tabindex="-1"></a><span class="co"># than the one defined in the base model</span></span>
|
||||
<span id="cb1-1115"><a href="#cb1-1115" 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="cb1-1116"><a href="#cb1-1116" aria-hidden="true" tabindex="-1"></a><span class="co"># use_fast option for tokenizer loading from_pretrained, default to True</span></span>
|
||||
<span id="cb1-1117"><a href="#cb1-1117" 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="cb1-1118"><a href="#cb1-1118" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use the legacy tokenizer setting, defaults to True</span></span>
|
||||
<span id="cb1-1119"><a href="#cb1-1119" 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="cb1-1120"><a href="#cb1-1120" 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="cb1-1121"><a href="#cb1-1121" aria-hidden="true" tabindex="-1"></a><span class="co"># common tokenizer.</span></span>
|
||||
<span id="cb1-1122"><a href="#cb1-1122" 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="cb1-1123"><a href="#cb1-1123" aria-hidden="true" tabindex="-1"></a><span class="co"># Corresponding tokenizer for the model AutoTokenizer is a good choice</span></span>
|
||||
<span id="cb1-1124"><a href="#cb1-1124" 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="cb1-1125"><a href="#cb1-1125" aria-hidden="true" tabindex="-1"></a><span class="co"># transformers processor class</span></span>
|
||||
<span id="cb1-1126"><a href="#cb1-1126" 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="cb1-1127"><a href="#cb1-1127" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to save jinja files for tokenizer, transformers default is True</span></span>
|
||||
<span id="cb1-1128"><a href="#cb1-1128" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_save_jinja_files</span><span class="kw">:</span><span class="at"> bool | None = True</span></span>
|
||||
<span id="cb1-1129"><a href="#cb1-1129" aria-hidden="true" tabindex="-1"></a><span class="co"># Trust remote code for untrusted source</span></span>
|
||||
<span id="cb1-1130"><a href="#cb1-1130" 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="cb1-1131"><a href="#cb1-1131" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1132"><a href="#cb1-1132" aria-hidden="true" tabindex="-1"></a><span class="co"># Don't move the model to the device before sharding. Set to `false` to revert to legacy</span></span>
|
||||
<span id="cb1-1133"><a href="#cb1-1133" aria-hidden="true" tabindex="-1"></a><span class="co"># behavior.</span></span>
|
||||
<span id="cb1-1134"><a href="#cb1-1134" aria-hidden="true" tabindex="-1"></a><span class="fu">experimental_skip_move_to_device</span><span class="kw">:</span><span class="at"> bool | None = True</span></span>
|
||||
<span id="cb1-1135"><a href="#cb1-1135" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1136"><a href="#cb1-1136" aria-hidden="true" tabindex="-1"></a><span class="co"># Use custom kernels, e.g. MegaBlocks.</span></span>
|
||||
<span id="cb1-1137"><a href="#cb1-1137" aria-hidden="true" tabindex="-1"></a><span class="fu">use_kernels</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1138"><a href="#cb1-1138" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1139"><a href="#cb1-1139" aria-hidden="true" tabindex="-1"></a><span class="co"># Model loading quantization config</span></span>
|
||||
<span id="cb1-1140"><a href="#cb1-1140" aria-hidden="true" tabindex="-1"></a><span class="fu">model_quantization_config</span><span class="kw">:</span><span class="at"> Literal['Mxfp4Config'] | None</span></span>
|
||||
<span id="cb1-1141"><a href="#cb1-1141" aria-hidden="true" tabindex="-1"></a><span class="co"># kwargs for model quantization config</span></span>
|
||||
<span id="cb1-1142"><a href="#cb1-1142" aria-hidden="true" tabindex="-1"></a><span class="fu">model_quantization_config_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1143"><a href="#cb1-1143" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1144"><a href="#cb1-1144" aria-hidden="true" tabindex="-1"></a><span class="co"># Where to save the full-finetuned model to</span></span>
|
||||
<span id="cb1-1145"><a href="#cb1-1145" 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="cb1-1146"><a href="#cb1-1146" aria-hidden="true" tabindex="-1"></a><span class="co"># push checkpoints to hub</span></span>
|
||||
<span id="cb1-1147"><a href="#cb1-1147" 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="cb1-1148"><a href="#cb1-1148" aria-hidden="true" tabindex="-1"></a><span class="co"># how to push checkpoints to hub</span></span>
|
||||
<span id="cb1-1149"><a href="#cb1-1149" 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="cb1-1150"><a href="#cb1-1150" aria-hidden="true" tabindex="-1"></a><span class="co"># Save model as safetensors (require safetensors package). Default True</span></span>
|
||||
<span id="cb1-1151"><a href="#cb1-1151" 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="cb1-1152"><a href="#cb1-1152" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1153"><a href="#cb1-1153" 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="cb1-1154"><a href="#cb1-1154" 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="cb1-1155"><a href="#cb1-1155" aria-hidden="true" tabindex="-1"></a><span class="co"># Use bitsandbytes 4 bit</span></span>
|
||||
<span id="cb1-1156"><a href="#cb1-1156" 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="cb1-1157"><a href="#cb1-1157" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1158"><a href="#cb1-1158" aria-hidden="true" tabindex="-1"></a><span class="co"># If you want to use 'lora' or 'qlora' or leave blank to train all parameters in</span></span>
|
||||
<span id="cb1-1159"><a href="#cb1-1159" aria-hidden="true" tabindex="-1"></a><span class="co"># original model</span></span>
|
||||
<span id="cb1-1160"><a href="#cb1-1160" aria-hidden="true" tabindex="-1"></a><span class="fu">adapter</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1161"><a href="#cb1-1161" 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="cb1-1162"><a href="#cb1-1162" 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="cb1-1163"><a href="#cb1-1163" 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="cb1-1164"><a href="#cb1-1164" aria-hidden="true" tabindex="-1"></a><span class="co"># subdirectory `merged` will be created under the `output_dir`.</span></span>
|
||||
<span id="cb1-1165"><a href="#cb1-1165" 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="cb1-1166"><a href="#cb1-1166" 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="cb1-1167"><a href="#cb1-1167" 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="cb1-1168"><a href="#cb1-1168" 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="cb1-1169"><a href="#cb1-1169" 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="cb1-1170"><a href="#cb1-1170" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_parameters</span><span class="kw">:</span><span class="at"> str | list[str] | None</span></span>
|
||||
<span id="cb1-1171"><a href="#cb1-1171" aria-hidden="true" tabindex="-1"></a><span class="co"># If true, will target all linear modules</span></span>
|
||||
<span id="cb1-1172"><a href="#cb1-1172" 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="cb1-1173"><a href="#cb1-1173" 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="cb1-1174"><a href="#cb1-1174" 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="cb1-1175"><a href="#cb1-1175" 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="cb1-1176"><a href="#cb1-1176" aria-hidden="true" tabindex="-1"></a><span class="co"># tokens to embeddings, and `lm_head` converts embeddings to token probabilities.</span></span>
|
||||
<span id="cb1-1177"><a href="#cb1-1177" 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="cb1-1178"><a href="#cb1-1178" 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="cb1-1179"><a href="#cb1-1179" aria-hidden="true" tabindex="-1"></a><span class="co"># The layer indices to transform, otherwise, apply to all layers</span></span>
|
||||
<span id="cb1-1180"><a href="#cb1-1180" 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="cb1-1181"><a href="#cb1-1181" 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="cb1-1182"><a href="#cb1-1182" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1183"><a href="#cb1-1183" aria-hidden="true" tabindex="-1"></a><span class="fu">peft</span><span class="kw">:</span><span class="at"> PeftConfig | None</span></span>
|
||||
<span id="cb1-1184"><a href="#cb1-1184" aria-hidden="true" tabindex="-1"></a><span class="co"> # For PeftConfig:</span></span>
|
||||
<span id="cb1-1185"><a href="#cb1-1185" aria-hidden="true" tabindex="-1"></a><span class="co"> # Configuration options for loftq initialization for LoRA</span></span>
|
||||
<span id="cb1-1186"><a href="#cb1-1186" 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="cb1-1187"><a href="#cb1-1187" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LoftQConfig:</span></span>
|
||||
<span id="cb1-1188"><a href="#cb1-1188" aria-hidden="true" tabindex="-1"></a><span class="co"> # typically 4 bits</span></span>
|
||||
<span id="cb1-1189"><a href="#cb1-1189" 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="cb1-1190"><a href="#cb1-1190" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1191"><a href="#cb1-1191" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use DoRA.</span></span>
|
||||
<span id="cb1-1192"><a href="#cb1-1192" 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="cb1-1193"><a href="#cb1-1193" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use RSLoRA.</span></span>
|
||||
<span id="cb1-1194"><a href="#cb1-1194" 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="cb1-1195"><a href="#cb1-1195" aria-hidden="true" tabindex="-1"></a><span class="co"># List of layer indices to replicate.</span></span>
|
||||
<span id="cb1-1196"><a href="#cb1-1196" 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="cb1-1197"><a href="#cb1-1197" 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="cb1-1198"><a href="#cb1-1198" 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="cb1-1199"><a href="#cb1-1199" aria-hidden="true" tabindex="-1"></a><span class="co"># A list of token indices to fine-tune on the `embed_tokens` layer. Otherwise, a dict</span></span>
|
||||
<span id="cb1-1200"><a href="#cb1-1200" aria-hidden="true" tabindex="-1"></a><span class="co"># mapping an embedding layer name to its trainable token indices. See</span></span>
|
||||
<span id="cb1-1201"><a href="#cb1-1201" aria-hidden="true" tabindex="-1"></a><span class="co"># https://huggingface.co/docs/peft/v0.17.0/en/developer_guides/lora#efficiently-train-</span></span>
|
||||
<span id="cb1-1202"><a href="#cb1-1202" aria-hidden="true" tabindex="-1"></a><span class="co"># tokens-alongside-lora</span></span>
|
||||
<span id="cb1-1203"><a href="#cb1-1203" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_trainable_token_indices</span><span class="kw">:</span><span class="at"> list[int] | dict[str, list[int]] | None</span></span>
|
||||
<span id="cb1-1204"><a href="#cb1-1204" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to tie adapter weights for tied model weights. See</span></span>
|
||||
<span id="cb1-1205"><a href="#cb1-1205" aria-hidden="true" tabindex="-1"></a><span class="co"># https://github.com/huggingface/peft/issues/2864</span></span>
|
||||
<span id="cb1-1206"><a href="#cb1-1206" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_ensure_weight_tying</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1207"><a href="#cb1-1207" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to upcast the LoRA adapter to fp32. This is enabled by default in PEFT.</span></span>
|
||||
<span id="cb1-1208"><a href="#cb1-1208" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_autocast_adapter_dtype</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1209"><a href="#cb1-1209" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1210"><a href="#cb1-1210" 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="cb1-1211"><a href="#cb1-1211" 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="cb1-1212"><a href="#cb1-1212" 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="cb1-1213"><a href="#cb1-1213" 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="cb1-1214"><a href="#cb1-1214" 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="cb1-1215"><a href="#cb1-1215" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether you are training a 4-bit GPTQ quantized model</span></span>
|
||||
<span id="cb1-1216"><a href="#cb1-1216" aria-hidden="true" tabindex="-1"></a><span class="fu">gptq</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1217"><a href="#cb1-1217" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the bnb 4bit quantization configuration</span></span>
|
||||
<span id="cb1-1218"><a href="#cb1-1218" 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="cb1-1219"><a href="#cb1-1219" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1220"><a href="#cb1-1220" 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="cb1-1221"><a href="#cb1-1221" 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="cb1-1222"><a href="#cb1-1222" 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="cb1-1223"><a href="#cb1-1223" 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="cb1-1224"><a href="#cb1-1224" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1225"><a href="#cb1-1225" 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="cb1-1112"><a href="#cb1-1112" aria-hidden="true" tabindex="-1"></a><span class="co"># transformers config class (e.g., 'LlamaConfig', 'MistralConfig'). Defaults to</span></span>
|
||||
<span id="cb1-1113"><a href="#cb1-1113" aria-hidden="true" tabindex="-1"></a><span class="co"># AutoConfig.</span></span>
|
||||
<span id="cb1-1114"><a href="#cb1-1114" 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="cb1-1115"><a href="#cb1-1115" 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="cb1-1116"><a href="#cb1-1116" aria-hidden="true" tabindex="-1"></a><span class="co"># than the one defined in the base model</span></span>
|
||||
<span id="cb1-1117"><a href="#cb1-1117" 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="cb1-1118"><a href="#cb1-1118" aria-hidden="true" tabindex="-1"></a><span class="co"># use_fast option for tokenizer loading from_pretrained, default to True</span></span>
|
||||
<span id="cb1-1119"><a href="#cb1-1119" 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="cb1-1120"><a href="#cb1-1120" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use the legacy tokenizer setting, defaults to True</span></span>
|
||||
<span id="cb1-1121"><a href="#cb1-1121" 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="cb1-1122"><a href="#cb1-1122" 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="cb1-1123"><a href="#cb1-1123" aria-hidden="true" tabindex="-1"></a><span class="co"># common tokenizer.</span></span>
|
||||
<span id="cb1-1124"><a href="#cb1-1124" 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="cb1-1125"><a href="#cb1-1125" aria-hidden="true" tabindex="-1"></a><span class="co"># Corresponding tokenizer for the model AutoTokenizer is a good choice</span></span>
|
||||
<span id="cb1-1126"><a href="#cb1-1126" 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="cb1-1127"><a href="#cb1-1127" aria-hidden="true" tabindex="-1"></a><span class="co"># transformers processor class</span></span>
|
||||
<span id="cb1-1128"><a href="#cb1-1128" 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="cb1-1129"><a href="#cb1-1129" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to save jinja files for tokenizer, transformers default is True</span></span>
|
||||
<span id="cb1-1130"><a href="#cb1-1130" aria-hidden="true" tabindex="-1"></a><span class="fu">tokenizer_save_jinja_files</span><span class="kw">:</span><span class="at"> bool | None = True</span></span>
|
||||
<span id="cb1-1131"><a href="#cb1-1131" aria-hidden="true" tabindex="-1"></a><span class="co"># Trust remote code for untrusted source</span></span>
|
||||
<span id="cb1-1132"><a href="#cb1-1132" 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="cb1-1133"><a href="#cb1-1133" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1134"><a href="#cb1-1134" aria-hidden="true" tabindex="-1"></a><span class="co"># Don't move the model to the device before sharding. Set to `false` to revert to legacy</span></span>
|
||||
<span id="cb1-1135"><a href="#cb1-1135" aria-hidden="true" tabindex="-1"></a><span class="co"># behavior.</span></span>
|
||||
<span id="cb1-1136"><a href="#cb1-1136" aria-hidden="true" tabindex="-1"></a><span class="fu">experimental_skip_move_to_device</span><span class="kw">:</span><span class="at"> bool | None = True</span></span>
|
||||
<span id="cb1-1137"><a href="#cb1-1137" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1138"><a href="#cb1-1138" aria-hidden="true" tabindex="-1"></a><span class="co"># Use custom kernels, e.g. MegaBlocks.</span></span>
|
||||
<span id="cb1-1139"><a href="#cb1-1139" aria-hidden="true" tabindex="-1"></a><span class="fu">use_kernels</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1140"><a href="#cb1-1140" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1141"><a href="#cb1-1141" aria-hidden="true" tabindex="-1"></a><span class="co"># Model loading quantization config</span></span>
|
||||
<span id="cb1-1142"><a href="#cb1-1142" aria-hidden="true" tabindex="-1"></a><span class="fu">model_quantization_config</span><span class="kw">:</span><span class="at"> Literal['Mxfp4Config'] | None</span></span>
|
||||
<span id="cb1-1143"><a href="#cb1-1143" aria-hidden="true" tabindex="-1"></a><span class="co"># kwargs for model quantization config</span></span>
|
||||
<span id="cb1-1144"><a href="#cb1-1144" aria-hidden="true" tabindex="-1"></a><span class="fu">model_quantization_config_kwargs</span><span class="kw">:</span><span class="at"> dict[str, Any] | None</span></span>
|
||||
<span id="cb1-1145"><a href="#cb1-1145" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1146"><a href="#cb1-1146" aria-hidden="true" tabindex="-1"></a><span class="co"># Where to save the full-finetuned model to</span></span>
|
||||
<span id="cb1-1147"><a href="#cb1-1147" 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="cb1-1148"><a href="#cb1-1148" aria-hidden="true" tabindex="-1"></a><span class="co"># push checkpoints to hub</span></span>
|
||||
<span id="cb1-1149"><a href="#cb1-1149" 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="cb1-1150"><a href="#cb1-1150" aria-hidden="true" tabindex="-1"></a><span class="co"># how to push checkpoints to hub</span></span>
|
||||
<span id="cb1-1151"><a href="#cb1-1151" 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="cb1-1152"><a href="#cb1-1152" aria-hidden="true" tabindex="-1"></a><span class="co"># Save model as safetensors (require safetensors package). Default True</span></span>
|
||||
<span id="cb1-1153"><a href="#cb1-1153" 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="cb1-1154"><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"># This will attempt to quantize the model down to 8 bits and use adam 8 bit optimizer</span></span>
|
||||
<span id="cb1-1156"><a href="#cb1-1156" 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="cb1-1157"><a href="#cb1-1157" aria-hidden="true" tabindex="-1"></a><span class="co"># Use bitsandbytes 4 bit</span></span>
|
||||
<span id="cb1-1158"><a href="#cb1-1158" 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="cb1-1159"><a href="#cb1-1159" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1160"><a href="#cb1-1160" 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="cb1-1161"><a href="#cb1-1161" aria-hidden="true" tabindex="-1"></a><span class="co"># original model</span></span>
|
||||
<span id="cb1-1162"><a href="#cb1-1162" aria-hidden="true" tabindex="-1"></a><span class="fu">adapter</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1163"><a href="#cb1-1163" 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="cb1-1164"><a href="#cb1-1164" 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="cb1-1165"><a href="#cb1-1165" 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="cb1-1166"><a href="#cb1-1166" aria-hidden="true" tabindex="-1"></a><span class="co"># subdirectory `merged` will be created under the `output_dir`.</span></span>
|
||||
<span id="cb1-1167"><a href="#cb1-1167" 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="cb1-1168"><a href="#cb1-1168" 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="cb1-1169"><a href="#cb1-1169" 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="cb1-1170"><a href="#cb1-1170" 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="cb1-1171"><a href="#cb1-1171" 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="cb1-1172"><a href="#cb1-1172" aria-hidden="true" tabindex="-1"></a><span class="fu">lora_target_parameters</span><span class="kw">:</span><span class="at"> str | list[str] | None</span></span>
|
||||
<span id="cb1-1173"><a href="#cb1-1173" aria-hidden="true" tabindex="-1"></a><span class="co"># If true, will target all linear modules</span></span>
|
||||
<span id="cb1-1174"><a href="#cb1-1174" 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="cb1-1175"><a href="#cb1-1175" 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="cb1-1176"><a href="#cb1-1176" 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="cb1-1177"><a href="#cb1-1177" 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="cb1-1178"><a href="#cb1-1178" aria-hidden="true" tabindex="-1"></a><span class="co"># tokens to embeddings, and `lm_head` converts embeddings to token probabilities.</span></span>
|
||||
<span id="cb1-1179"><a href="#cb1-1179" 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="cb1-1180"><a href="#cb1-1180" 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="cb1-1181"><a href="#cb1-1181" aria-hidden="true" tabindex="-1"></a><span class="co"># The layer indices to transform, otherwise, apply to all layers</span></span>
|
||||
<span id="cb1-1182"><a href="#cb1-1182" 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="cb1-1183"><a href="#cb1-1183" 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="cb1-1184"><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">peft</span><span class="kw">:</span><span class="at"> PeftConfig | None</span></span>
|
||||
<span id="cb1-1186"><a href="#cb1-1186" aria-hidden="true" tabindex="-1"></a><span class="co"> # For PeftConfig:</span></span>
|
||||
<span id="cb1-1187"><a href="#cb1-1187" aria-hidden="true" tabindex="-1"></a><span class="co"> # Configuration options for loftq initialization for LoRA</span></span>
|
||||
<span id="cb1-1188"><a href="#cb1-1188" 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="cb1-1189"><a href="#cb1-1189" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LoftQConfig:</span></span>
|
||||
<span id="cb1-1190"><a href="#cb1-1190" aria-hidden="true" tabindex="-1"></a><span class="co"> # typically 4 bits</span></span>
|
||||
<span id="cb1-1191"><a href="#cb1-1191" 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="cb1-1192"><a href="#cb1-1192" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1193"><a href="#cb1-1193" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use DoRA.</span></span>
|
||||
<span id="cb1-1194"><a href="#cb1-1194" 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="cb1-1195"><a href="#cb1-1195" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use RSLoRA.</span></span>
|
||||
<span id="cb1-1196"><a href="#cb1-1196" 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="cb1-1197"><a href="#cb1-1197" aria-hidden="true" tabindex="-1"></a><span class="co"># List of layer indices to replicate.</span></span>
|
||||
<span id="cb1-1198"><a href="#cb1-1198" 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="cb1-1199"><a href="#cb1-1199" 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="cb1-1200"><a href="#cb1-1200" 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="cb1-1201"><a href="#cb1-1201" aria-hidden="true" tabindex="-1"></a><span class="co"># A list of token indices to fine-tune on the `embed_tokens` layer. Otherwise, a dict</span></span>
|
||||
<span id="cb1-1202"><a href="#cb1-1202" aria-hidden="true" tabindex="-1"></a><span class="co"># mapping an embedding layer name to its trainable token indices. See</span></span>
|
||||
<span id="cb1-1203"><a href="#cb1-1203" aria-hidden="true" tabindex="-1"></a><span class="co"># https://huggingface.co/docs/peft/v0.17.0/en/developer_guides/lora#efficiently-train-</span></span>
|
||||
<span id="cb1-1204"><a href="#cb1-1204" aria-hidden="true" tabindex="-1"></a><span class="co"># tokens-alongside-lora</span></span>
|
||||
<span id="cb1-1205"><a href="#cb1-1205" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_trainable_token_indices</span><span class="kw">:</span><span class="at"> list[int] | dict[str, list[int]] | None</span></span>
|
||||
<span id="cb1-1206"><a href="#cb1-1206" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to tie adapter weights for tied model weights. See</span></span>
|
||||
<span id="cb1-1207"><a href="#cb1-1207" aria-hidden="true" tabindex="-1"></a><span class="co"># https://github.com/huggingface/peft/issues/2864</span></span>
|
||||
<span id="cb1-1208"><a href="#cb1-1208" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_ensure_weight_tying</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1209"><a href="#cb1-1209" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to upcast the LoRA adapter to fp32. This is enabled by default in PEFT.</span></span>
|
||||
<span id="cb1-1210"><a href="#cb1-1210" aria-hidden="true" tabindex="-1"></a><span class="fu">peft_autocast_adapter_dtype</span><span class="kw">:</span><span class="at"> bool | 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="co"># load qlora model in sharded format for FSDP using answer.ai technique.</span></span>
|
||||
<span id="cb1-1213"><a href="#cb1-1213" 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="cb1-1214"><a href="#cb1-1214" 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="cb1-1215"><a href="#cb1-1215" 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="cb1-1216"><a href="#cb1-1216" 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="cb1-1217"><a href="#cb1-1217" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether you are training a 4-bit GPTQ quantized model</span></span>
|
||||
<span id="cb1-1218"><a href="#cb1-1218" aria-hidden="true" tabindex="-1"></a><span class="fu">gptq</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1219"><a href="#cb1-1219" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the bnb 4bit quantization configuration</span></span>
|
||||
<span id="cb1-1220"><a href="#cb1-1220" 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="cb1-1221"><a href="#cb1-1221" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1222"><a href="#cb1-1222" aria-hidden="true" tabindex="-1"></a><span class="co"># loraplus learning rate ratio lr_B / lr_A. Recommended value is 2^4.</span></span>
|
||||
<span id="cb1-1223"><a href="#cb1-1223" 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="cb1-1224"><a href="#cb1-1224" 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="cb1-1225"><a href="#cb1-1225" 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="cb1-1226"><a href="#cb1-1226" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1227"><a href="#cb1-1227" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use ReLoRA. Use with jagged_restart_*steps options.</span></span>
|
||||
<span id="cb1-1228"><a href="#cb1-1228" aria-hidden="true" tabindex="-1"></a><span class="fu">relora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1229"><a href="#cb1-1229" aria-hidden="true" tabindex="-1"></a><span class="co"># threshold for optimizer magnitude when pruning</span></span>
|
||||
<span id="cb1-1230"><a href="#cb1-1230" 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="cb1-1231"><a href="#cb1-1231" 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="cb1-1232"><a href="#cb1-1232" aria-hidden="true" tabindex="-1"></a><span class="co"># savings</span></span>
|
||||
<span id="cb1-1233"><a href="#cb1-1233" 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="cb1-1234"><a href="#cb1-1234" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1235"><a href="#cb1-1235" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to reset for jagged restarts</span></span>
|
||||
<span id="cb1-1236"><a href="#cb1-1236" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1237"><a href="#cb1-1237" aria-hidden="true" tabindex="-1"></a><span class="co"># how many warmup steps to take after reset for jagged restarts</span></span>
|
||||
<span id="cb1-1238"><a href="#cb1-1238" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_warmup_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1239"><a href="#cb1-1239" aria-hidden="true" tabindex="-1"></a><span class="co"># how many anneal steps to take before reset for jagged restarts</span></span>
|
||||
<span id="cb1-1240"><a href="#cb1-1240" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_anneal_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1241"><a href="#cb1-1241" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1242"><a href="#cb1-1242" 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="cb1-1243"><a href="#cb1-1243" aria-hidden="true" tabindex="-1"></a><span class="co"># accumulated for the given number of steps.</span></span>
|
||||
<span id="cb1-1244"><a href="#cb1-1244" 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="cb1-1245"><a href="#cb1-1245" 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="cb1-1246"><a href="#cb1-1246" 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="cb1-1247"><a href="#cb1-1247" 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="cb1-1248"><a href="#cb1-1248" aria-hidden="true" tabindex="-1"></a><span class="co"># Total batch size, we do not recommended setting this manually</span></span>
|
||||
<span id="cb1-1249"><a href="#cb1-1249" 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="cb1-1250"><a href="#cb1-1250" 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="cb1-1251"><a href="#cb1-1251" 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="cb1-1252"><a href="#cb1-1252" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1253"><a href="#cb1-1253" 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="cb1-1254"><a href="#cb1-1254" aria-hidden="true" tabindex="-1"></a><span class="co"># Trainer</span></span>
|
||||
<span id="cb1-1255"><a href="#cb1-1255" 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="cb1-1256"><a href="#cb1-1256" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1257"><a href="#cb1-1257" 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="cb1-1258"><a href="#cb1-1258" 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="cb1-1259"><a href="#cb1-1259" 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="cb1-1260"><a href="#cb1-1260" 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="cb1-1261"><a href="#cb1-1261" aria-hidden="true" tabindex="-1"></a><span class="co"># pattern with this enabled.</span></span>
|
||||
<span id="cb1-1262"><a href="#cb1-1262" 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="cb1-1263"><a href="#cb1-1263" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1264"><a href="#cb1-1264" aria-hidden="true" tabindex="-1"></a><span class="fu">learning_rate</span><span class="kw">:</span><span class="at"> str | float (required)</span></span>
|
||||
<span id="cb1-1265"><a href="#cb1-1265" 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="cb1-1266"><a href="#cb1-1266" 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="cb1-1267"><a href="#cb1-1267" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify weight decay</span></span>
|
||||
<span id="cb1-1268"><a href="#cb1-1268" 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="cb1-1269"><a href="#cb1-1269" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify optimizer</span></span>
|
||||
<span id="cb1-1270"><a href="#cb1-1270" 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="cb1-1271"><a href="#cb1-1271" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary of arguments to pass to the optimizer</span></span>
|
||||
<span id="cb1-1272"><a href="#cb1-1272" 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="cb1-1273"><a href="#cb1-1273" 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="cb1-1274"><a href="#cb1-1274" aria-hidden="true" tabindex="-1"></a><span class="co"># right now this is used only for GaLore algorithm</span></span>
|
||||
<span id="cb1-1275"><a href="#cb1-1275" 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="cb1-1276"><a href="#cb1-1276" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
|
||||
<span id="cb1-1277"><a href="#cb1-1277" 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="cb1-1278"><a href="#cb1-1278" 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="cb1-1279"><a href="#cb1-1279" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify a scheduler and kwargs to use with the optimizer</span></span>
|
||||
<span id="cb1-1280"><a href="#cb1-1280" 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="cb1-1281"><a href="#cb1-1281" 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="cb1-1282"><a href="#cb1-1282" 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="cb1-1283"><a href="#cb1-1283" aria-hidden="true" tabindex="-1"></a><span class="co"># peak lr</span></span>
|
||||
<span id="cb1-1284"><a href="#cb1-1284" 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="cb1-1285"><a href="#cb1-1285" 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="cb1-1286"><a href="#cb1-1286" aria-hidden="true" tabindex="-1"></a><span class="co"># start cosine_min_lr at 80% of training step</span></span>
|
||||
<span id="cb1-1287"><a href="#cb1-1287" 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="cb1-1288"><a href="#cb1-1288" aria-hidden="true" tabindex="-1"></a><span class="co"># Learning rate div factor</span></span>
|
||||
<span id="cb1-1289"><a href="#cb1-1289" 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="cb1-1290"><a href="#cb1-1290" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1291"><a href="#cb1-1291" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_groups</span><span class="kw">:</span><span class="at"> list[LrGroup] | None</span></span>
|
||||
<span id="cb1-1292"><a href="#cb1-1292" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LrGroup:</span></span>
|
||||
<span id="cb1-1293"><a href="#cb1-1293" 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="cb1-1294"><a href="#cb1-1294" 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="cb1-1295"><a href="#cb1-1295" 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="cb1-1296"><a href="#cb1-1296" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1297"><a href="#cb1-1297" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1298"><a href="#cb1-1298" 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="cb1-1299"><a href="#cb1-1299" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1300"><a href="#cb1-1300" 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="cb1-1301"><a href="#cb1-1301" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1302"><a href="#cb1-1302" 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="cb1-1227"><a href="#cb1-1227" 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="cb1-1228"><a href="#cb1-1228" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1229"><a href="#cb1-1229" aria-hidden="true" tabindex="-1"></a><span class="co"># Whether to use ReLoRA. Use with jagged_restart_*steps options.</span></span>
|
||||
<span id="cb1-1230"><a href="#cb1-1230" aria-hidden="true" tabindex="-1"></a><span class="fu">relora</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1231"><a href="#cb1-1231" aria-hidden="true" tabindex="-1"></a><span class="co"># threshold for optimizer magnitude when pruning</span></span>
|
||||
<span id="cb1-1232"><a href="#cb1-1232" 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="cb1-1233"><a href="#cb1-1233" 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="cb1-1234"><a href="#cb1-1234" aria-hidden="true" tabindex="-1"></a><span class="co"># savings</span></span>
|
||||
<span id="cb1-1235"><a href="#cb1-1235" 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="cb1-1236"><a href="#cb1-1236" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1237"><a href="#cb1-1237" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to reset for jagged restarts</span></span>
|
||||
<span id="cb1-1238"><a href="#cb1-1238" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1239"><a href="#cb1-1239" aria-hidden="true" tabindex="-1"></a><span class="co"># how many warmup steps to take after reset for jagged restarts</span></span>
|
||||
<span id="cb1-1240"><a href="#cb1-1240" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_warmup_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1241"><a href="#cb1-1241" aria-hidden="true" tabindex="-1"></a><span class="co"># how many anneal steps to take before reset for jagged restarts</span></span>
|
||||
<span id="cb1-1242"><a href="#cb1-1242" aria-hidden="true" tabindex="-1"></a><span class="fu">jagged_restart_anneal_steps</span><span class="kw">:</span><span class="at"> int | None</span></span>
|
||||
<span id="cb1-1243"><a href="#cb1-1243" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1244"><a href="#cb1-1244" 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="cb1-1245"><a href="#cb1-1245" aria-hidden="true" tabindex="-1"></a><span class="co"># accumulated for the given number of steps.</span></span>
|
||||
<span id="cb1-1246"><a href="#cb1-1246" 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="cb1-1247"><a href="#cb1-1247" 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="cb1-1248"><a href="#cb1-1248" 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="cb1-1249"><a href="#cb1-1249" 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="cb1-1250"><a href="#cb1-1250" aria-hidden="true" tabindex="-1"></a><span class="co"># Total batch size, we do not recommended setting this manually</span></span>
|
||||
<span id="cb1-1251"><a href="#cb1-1251" 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="cb1-1252"><a href="#cb1-1252" 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="cb1-1253"><a href="#cb1-1253" 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="cb1-1254"><a href="#cb1-1254" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1255"><a href="#cb1-1255" 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="cb1-1256"><a href="#cb1-1256" aria-hidden="true" tabindex="-1"></a><span class="co"># Trainer</span></span>
|
||||
<span id="cb1-1257"><a href="#cb1-1257" 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="cb1-1258"><a href="#cb1-1258" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1259"><a href="#cb1-1259" 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="cb1-1260"><a href="#cb1-1260" 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="cb1-1261"><a href="#cb1-1261" 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="cb1-1262"><a href="#cb1-1262" 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="cb1-1263"><a href="#cb1-1263" aria-hidden="true" tabindex="-1"></a><span class="co"># pattern with this enabled.</span></span>
|
||||
<span id="cb1-1264"><a href="#cb1-1264" 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="cb1-1265"><a href="#cb1-1265" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1266"><a href="#cb1-1266" aria-hidden="true" tabindex="-1"></a><span class="fu">learning_rate</span><span class="kw">:</span><span class="at"> str | float (required)</span></span>
|
||||
<span id="cb1-1267"><a href="#cb1-1267" 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="cb1-1268"><a href="#cb1-1268" 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="cb1-1269"><a href="#cb1-1269" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify weight decay</span></span>
|
||||
<span id="cb1-1270"><a href="#cb1-1270" 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="cb1-1271"><a href="#cb1-1271" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify optimizer</span></span>
|
||||
<span id="cb1-1272"><a href="#cb1-1272" 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="cb1-1273"><a href="#cb1-1273" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary of arguments to pass to the optimizer</span></span>
|
||||
<span id="cb1-1274"><a href="#cb1-1274" 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="cb1-1275"><a href="#cb1-1275" 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="cb1-1276"><a href="#cb1-1276" aria-hidden="true" tabindex="-1"></a><span class="co"># right now this is used only for GaLore algorithm</span></span>
|
||||
<span id="cb1-1277"><a href="#cb1-1277" 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="cb1-1278"><a href="#cb1-1278" aria-hidden="true" tabindex="-1"></a><span class="co"># Path to torch distx for optim 'adamw_anyprecision'</span></span>
|
||||
<span id="cb1-1279"><a href="#cb1-1279" 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="cb1-1280"><a href="#cb1-1280" 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="cb1-1281"><a href="#cb1-1281" aria-hidden="true" tabindex="-1"></a><span class="co"># Specify a scheduler and kwargs to use with the optimizer</span></span>
|
||||
<span id="cb1-1282"><a href="#cb1-1282" 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="cb1-1283"><a href="#cb1-1283" 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="cb1-1284"><a href="#cb1-1284" 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="cb1-1285"><a href="#cb1-1285" aria-hidden="true" tabindex="-1"></a><span class="co"># peak lr</span></span>
|
||||
<span id="cb1-1286"><a href="#cb1-1286" 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="cb1-1287"><a href="#cb1-1287" 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="cb1-1288"><a href="#cb1-1288" aria-hidden="true" tabindex="-1"></a><span class="co"># start cosine_min_lr at 80% of training step</span></span>
|
||||
<span id="cb1-1289"><a href="#cb1-1289" 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="cb1-1290"><a href="#cb1-1290" aria-hidden="true" tabindex="-1"></a><span class="co"># Learning rate div factor</span></span>
|
||||
<span id="cb1-1291"><a href="#cb1-1291" 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="cb1-1292"><a href="#cb1-1292" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1293"><a href="#cb1-1293" aria-hidden="true" tabindex="-1"></a><span class="fu">lr_groups</span><span class="kw">:</span><span class="at"> list[LrGroup] | None</span></span>
|
||||
<span id="cb1-1294"><a href="#cb1-1294" aria-hidden="true" tabindex="-1"></a><span class="co"> # For LrGroup:</span></span>
|
||||
<span id="cb1-1295"><a href="#cb1-1295" 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="cb1-1296"><a href="#cb1-1296" 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="cb1-1297"><a href="#cb1-1297" 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="cb1-1298"><a href="#cb1-1298" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1299"><a href="#cb1-1299" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1300"><a href="#cb1-1300" 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="cb1-1301"><a href="#cb1-1301" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1302"><a href="#cb1-1302" 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="cb1-1303"><a href="#cb1-1303" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1304"><a href="#cb1-1304" 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="cb1-1305"><a href="#cb1-1305" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1306"><a href="#cb1-1306" 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="cb1-1307"><a href="#cb1-1307" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1308"><a href="#cb1-1308" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer learning rate</span></span>
|
||||
<span id="cb1-1309"><a href="#cb1-1309" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_lr</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1310"><a href="#cb1-1310" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer momentum</span></span>
|
||||
<span id="cb1-1311"><a href="#cb1-1311" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_momentum</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1312"><a href="#cb1-1312" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: r/d fraction for low-rank approximation. Used to compute the low-rank</span></span>
|
||||
<span id="cb1-1313"><a href="#cb1-1313" aria-hidden="true" tabindex="-1"></a><span class="co"># dimension.</span></span>
|
||||
<span id="cb1-1314"><a href="#cb1-1314" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_fraction</span><span class="kw">:</span><span class="at"> float | None = 1.0</span></span>
|
||||
<span id="cb1-1315"><a href="#cb1-1315" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: Round up the low-rank dimension to a multiple of this number. This may</span></span>
|
||||
<span id="cb1-1316"><a href="#cb1-1316" aria-hidden="true" tabindex="-1"></a><span class="co"># be useful to ensure even sharding.</span></span>
|
||||
<span id="cb1-1317"><a href="#cb1-1317" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_multiple_of</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1318"><a href="#cb1-1318" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1319"><a href="#cb1-1319" aria-hidden="true" tabindex="-1"></a><span class="co"># Gradient clipping max norm</span></span>
|
||||
<span id="cb1-1320"><a href="#cb1-1320" 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="cb1-1321"><a href="#cb1-1321" 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="cb1-1322"><a href="#cb1-1322" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1323"><a href="#cb1-1323" aria-hidden="true" tabindex="-1"></a><span class="fu">use_wandb</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1324"><a href="#cb1-1324" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your wandb run</span></span>
|
||||
<span id="cb1-1325"><a href="#cb1-1325" 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="cb1-1326"><a href="#cb1-1326" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the ID of your wandb run</span></span>
|
||||
<span id="cb1-1327"><a href="#cb1-1327" 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="cb1-1328"><a href="#cb1-1328" 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="cb1-1329"><a href="#cb1-1329" aria-hidden="true" tabindex="-1"></a><span class="co"># off wandb</span></span>
|
||||
<span id="cb1-1330"><a href="#cb1-1330" 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="cb1-1331"><a href="#cb1-1331" aria-hidden="true" tabindex="-1"></a><span class="co"># Your wandb project name</span></span>
|
||||
<span id="cb1-1332"><a href="#cb1-1332" 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="cb1-1333"><a href="#cb1-1333" aria-hidden="true" tabindex="-1"></a><span class="co"># A wandb Team name if using a Team</span></span>
|
||||
<span id="cb1-1334"><a href="#cb1-1334" 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="cb1-1335"><a href="#cb1-1335" 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="cb1-1336"><a href="#cb1-1336" 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="cb1-1337"><a href="#cb1-1337" aria-hidden="true" tabindex="-1"></a><span class="co"># at the end of training</span></span>
|
||||
<span id="cb1-1338"><a href="#cb1-1338" 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="cb1-1339"><a href="#cb1-1339" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1340"><a href="#cb1-1340" 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="cb1-1341"><a href="#cb1-1341" aria-hidden="true" tabindex="-1"></a><span class="co"># URI to mlflow</span></span>
|
||||
<span id="cb1-1342"><a href="#cb1-1342" 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="cb1-1343"><a href="#cb1-1343" aria-hidden="true" tabindex="-1"></a><span class="co"># Your experiment name</span></span>
|
||||
<span id="cb1-1344"><a href="#cb1-1344" 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="cb1-1345"><a href="#cb1-1345" aria-hidden="true" tabindex="-1"></a><span class="co"># Your run name</span></span>
|
||||
<span id="cb1-1346"><a href="#cb1-1346" 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="cb1-1347"><a href="#cb1-1347" 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="cb1-1348"><a href="#cb1-1348" 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="cb1-1349"><a href="#cb1-1349" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1350"><a href="#cb1-1350" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable or disable Comet integration.</span></span>
|
||||
<span id="cb1-1351"><a href="#cb1-1351" 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="cb1-1352"><a href="#cb1-1352" aria-hidden="true" tabindex="-1"></a><span class="co"># API key for Comet. Recommended to set via `comet login`.</span></span>
|
||||
<span id="cb1-1353"><a href="#cb1-1353" 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="cb1-1354"><a href="#cb1-1354" aria-hidden="true" tabindex="-1"></a><span class="co"># Workspace name in Comet. Defaults to the user's default workspace.</span></span>
|
||||
<span id="cb1-1355"><a href="#cb1-1355" 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="cb1-1356"><a href="#cb1-1356" aria-hidden="true" tabindex="-1"></a><span class="co"># Project name in Comet. Defaults to Uncategorized.</span></span>
|
||||
<span id="cb1-1357"><a href="#cb1-1357" 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="cb1-1358"><a href="#cb1-1358" 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="cb1-1359"><a href="#cb1-1359" aria-hidden="true" tabindex="-1"></a><span class="co"># control the key of new experiments. Default to a random key.</span></span>
|
||||
<span id="cb1-1360"><a href="#cb1-1360" 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="cb1-1361"><a href="#cb1-1361" 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="cb1-1362"><a href="#cb1-1362" aria-hidden="true" tabindex="-1"></a><span class="co"># ("get_or_create") auto-selects based on configuration.</span></span>
|
||||
<span id="cb1-1363"><a href="#cb1-1363" 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="cb1-1364"><a href="#cb1-1364" 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="cb1-1365"><a href="#cb1-1365" aria-hidden="true" tabindex="-1"></a><span class="co"># True.</span></span>
|
||||
<span id="cb1-1366"><a href="#cb1-1366" 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="cb1-1367"><a href="#cb1-1367" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary for additional configuration settings, see the doc for more details.</span></span>
|
||||
<span id="cb1-1368"><a href="#cb1-1368" 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="cb1-1369"><a href="#cb1-1369" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1370"><a href="#cb1-1370" aria-hidden="true" tabindex="-1"></a><span class="fu">use_trackio</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1371"><a href="#cb1-1371" aria-hidden="true" tabindex="-1"></a><span class="co"># Your trackio project name</span></span>
|
||||
<span id="cb1-1372"><a href="#cb1-1372" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_project_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1373"><a href="#cb1-1373" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your trackio run</span></span>
|
||||
<span id="cb1-1374"><a href="#cb1-1374" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1375"><a href="#cb1-1375" aria-hidden="true" tabindex="-1"></a><span class="co"># Hugging Face Space ID to sync dashboard to (optional, runs locally if not provided)</span></span>
|
||||
<span id="cb1-1376"><a href="#cb1-1376" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_space_id</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1377"><a href="#cb1-1377" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1378"><a href="#cb1-1378" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable OpenTelemetry metrics collection and Prometheus export</span></span>
|
||||
<span id="cb1-1379"><a href="#cb1-1379" aria-hidden="true" tabindex="-1"></a><span class="fu">use_otel_metrics</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1380"><a href="#cb1-1380" aria-hidden="true" tabindex="-1"></a><span class="co"># Host to bind the OpenTelemetry metrics server to</span></span>
|
||||
<span id="cb1-1381"><a href="#cb1-1381" aria-hidden="true" tabindex="-1"></a><span class="fu">otel_metrics_host</span><span class="kw">:</span><span class="at"> str | None = localhost</span></span>
|
||||
<span id="cb1-1382"><a href="#cb1-1382" aria-hidden="true" tabindex="-1"></a><span class="co"># Port for the Prometheus metrics HTTP server</span></span>
|
||||
<span id="cb1-1383"><a href="#cb1-1383" aria-hidden="true" tabindex="-1"></a><span class="fu">otel_metrics_port</span><span class="kw">:</span><span class="at"> int | None = 8000</span></span>
|
||||
<span id="cb1-1384"><a href="#cb1-1384" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1385"><a href="#cb1-1385" aria-hidden="true" tabindex="-1"></a><span class="co"># the number of activate layers in LISA</span></span>
|
||||
<span id="cb1-1386"><a href="#cb1-1386" 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="cb1-1387"><a href="#cb1-1387" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to switch layers in LISA</span></span>
|
||||
<span id="cb1-1388"><a href="#cb1-1388" 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="cb1-1389"><a href="#cb1-1389" aria-hidden="true" tabindex="-1"></a><span class="co"># path under the model to access the layers</span></span>
|
||||
<span id="cb1-1390"><a href="#cb1-1390" 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="cb1-1391"><a href="#cb1-1391" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1392"><a href="#cb1-1392" 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="cb1-1393"><a href="#cb1-1393" 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="cb1-1394"><a href="#cb1-1394" 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="cb1-1395"><a href="#cb1-1395" 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="cb1-1396"><a href="#cb1-1396" 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="cb1-1397"><a href="#cb1-1397" 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="cb1-1398"><a href="#cb1-1398" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1399"><a href="#cb1-1399" 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="cb1-1400"><a href="#cb1-1400" 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="cb1-1401"><a href="#cb1-1401" 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="cb1-1402"><a href="#cb1-1402" 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="cb1-1403"><a href="#cb1-1403" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1404"><a href="#cb1-1404" 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="cb1-1405"><a href="#cb1-1405" 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="cb1-1406"><a href="#cb1-1406" aria-hidden="true" tabindex="-1"></a><span class="co"># preprocessor.size, otherwise, images won't be resized.</span></span>
|
||||
<span id="cb1-1407"><a href="#cb1-1407" 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="cb1-1408"><a href="#cb1-1408" 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="cb1-1409"><a href="#cb1-1409" aria-hidden="true" tabindex="-1"></a><span class="co"># to PIL.Image.Resampling for more details.</span></span>
|
||||
<span id="cb1-1410"><a href="#cb1-1410" 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="cb1-1411"><a href="#cb1-1411" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1412"><a href="#cb1-1412" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the base model configuration</span></span>
|
||||
<span id="cb1-1413"><a href="#cb1-1413" 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="cb1-1414"><a href="#cb1-1414" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides the base model loading from_pretrained</span></span>
|
||||
<span id="cb1-1415"><a href="#cb1-1415" 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="cb1-1416"><a href="#cb1-1416" 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="cb1-1417"><a href="#cb1-1417" aria-hidden="true" tabindex="-1"></a><span class="co"># choice too</span></span>
|
||||
<span id="cb1-1418"><a href="#cb1-1418" 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="cb1-1419"><a href="#cb1-1419" 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="cb1-1420"><a href="#cb1-1420" 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="cb1-1421"><a href="#cb1-1421" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1422"><a href="#cb1-1422" 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="cb1-1423"><a href="#cb1-1423" 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="cb1-1424"><a href="#cb1-1424" 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="cb1-1425"><a href="#cb1-1425" 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="cb1-1426"><a href="#cb1-1426" aria-hidden="true" tabindex="-1"></a><span class="fu">evaluation_strategy</span><span class="kw">:</span><span class="at"> str | None</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
<span id="cb1-1304"><a href="#cb1-1304" 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="cb1-1305"><a href="#cb1-1305" aria-hidden="true" tabindex="-1"></a><span class="co"># adamw hyperparams</span></span>
|
||||
<span id="cb1-1306"><a href="#cb1-1306" 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="cb1-1307"><a href="#cb1-1307" aria-hidden="true" tabindex="-1"></a><span class="co"># only used for CAME Optimizer</span></span>
|
||||
<span id="cb1-1308"><a href="#cb1-1308" 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="cb1-1309"><a href="#cb1-1309" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1310"><a href="#cb1-1310" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer learning rate</span></span>
|
||||
<span id="cb1-1311"><a href="#cb1-1311" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_lr</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1312"><a href="#cb1-1312" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer momentum</span></span>
|
||||
<span id="cb1-1313"><a href="#cb1-1313" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_momentum</span><span class="kw">:</span><span class="at"> float | None</span></span>
|
||||
<span id="cb1-1314"><a href="#cb1-1314" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: r/d fraction for low-rank approximation. Used to compute the low-rank</span></span>
|
||||
<span id="cb1-1315"><a href="#cb1-1315" aria-hidden="true" tabindex="-1"></a><span class="co"># dimension.</span></span>
|
||||
<span id="cb1-1316"><a href="#cb1-1316" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_fraction</span><span class="kw">:</span><span class="at"> float | None = 1.0</span></span>
|
||||
<span id="cb1-1317"><a href="#cb1-1317" aria-hidden="true" tabindex="-1"></a><span class="co"># Dion Optimizer: Round up the low-rank dimension to a multiple of this number. This may</span></span>
|
||||
<span id="cb1-1318"><a href="#cb1-1318" aria-hidden="true" tabindex="-1"></a><span class="co"># be useful to ensure even sharding.</span></span>
|
||||
<span id="cb1-1319"><a href="#cb1-1319" aria-hidden="true" tabindex="-1"></a><span class="fu">dion_rank_multiple_of</span><span class="kw">:</span><span class="at"> int | None = 1</span></span>
|
||||
<span id="cb1-1320"><a href="#cb1-1320" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1321"><a href="#cb1-1321" aria-hidden="true" tabindex="-1"></a><span class="co"># Gradient clipping max norm</span></span>
|
||||
<span id="cb1-1322"><a href="#cb1-1322" 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="cb1-1323"><a href="#cb1-1323" 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="cb1-1324"><a href="#cb1-1324" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1325"><a href="#cb1-1325" 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="cb1-1326"><a href="#cb1-1326" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your wandb run</span></span>
|
||||
<span id="cb1-1327"><a href="#cb1-1327" 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="cb1-1328"><a href="#cb1-1328" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the ID of your wandb run</span></span>
|
||||
<span id="cb1-1329"><a href="#cb1-1329" 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="cb1-1330"><a href="#cb1-1330" 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="cb1-1331"><a href="#cb1-1331" aria-hidden="true" tabindex="-1"></a><span class="co"># off wandb</span></span>
|
||||
<span id="cb1-1332"><a href="#cb1-1332" 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="cb1-1333"><a href="#cb1-1333" aria-hidden="true" tabindex="-1"></a><span class="co"># Your wandb project name</span></span>
|
||||
<span id="cb1-1334"><a href="#cb1-1334" 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="cb1-1335"><a href="#cb1-1335" aria-hidden="true" tabindex="-1"></a><span class="co"># A wandb Team name if using a Team</span></span>
|
||||
<span id="cb1-1336"><a href="#cb1-1336" 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="cb1-1337"><a href="#cb1-1337" 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="cb1-1338"><a href="#cb1-1338" 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="cb1-1339"><a href="#cb1-1339" aria-hidden="true" tabindex="-1"></a><span class="co"># at the end of training</span></span>
|
||||
<span id="cb1-1340"><a href="#cb1-1340" 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="cb1-1341"><a href="#cb1-1341" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1342"><a href="#cb1-1342" 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="cb1-1343"><a href="#cb1-1343" aria-hidden="true" tabindex="-1"></a><span class="co"># URI to mlflow</span></span>
|
||||
<span id="cb1-1344"><a href="#cb1-1344" 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="cb1-1345"><a href="#cb1-1345" aria-hidden="true" tabindex="-1"></a><span class="co"># Your experiment name</span></span>
|
||||
<span id="cb1-1346"><a href="#cb1-1346" 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="cb1-1347"><a href="#cb1-1347" aria-hidden="true" tabindex="-1"></a><span class="co"># Your run name</span></span>
|
||||
<span id="cb1-1348"><a href="#cb1-1348" 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="cb1-1349"><a href="#cb1-1349" 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="cb1-1350"><a href="#cb1-1350" 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="cb1-1351"><a href="#cb1-1351" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1352"><a href="#cb1-1352" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable or disable Comet integration.</span></span>
|
||||
<span id="cb1-1353"><a href="#cb1-1353" 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="cb1-1354"><a href="#cb1-1354" aria-hidden="true" tabindex="-1"></a><span class="co"># API key for Comet. Recommended to set via `comet login`.</span></span>
|
||||
<span id="cb1-1355"><a href="#cb1-1355" 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="cb1-1356"><a href="#cb1-1356" aria-hidden="true" tabindex="-1"></a><span class="co"># Workspace name in Comet. Defaults to the user's default workspace.</span></span>
|
||||
<span id="cb1-1357"><a href="#cb1-1357" 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="cb1-1358"><a href="#cb1-1358" aria-hidden="true" tabindex="-1"></a><span class="co"># Project name in Comet. Defaults to Uncategorized.</span></span>
|
||||
<span id="cb1-1359"><a href="#cb1-1359" 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="cb1-1360"><a href="#cb1-1360" 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="cb1-1361"><a href="#cb1-1361" aria-hidden="true" tabindex="-1"></a><span class="co"># control the key of new experiments. Default to a random key.</span></span>
|
||||
<span id="cb1-1362"><a href="#cb1-1362" 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="cb1-1363"><a href="#cb1-1363" 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="cb1-1364"><a href="#cb1-1364" aria-hidden="true" tabindex="-1"></a><span class="co"># ("get_or_create") auto-selects based on configuration.</span></span>
|
||||
<span id="cb1-1365"><a href="#cb1-1365" 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="cb1-1366"><a href="#cb1-1366" 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="cb1-1367"><a href="#cb1-1367" aria-hidden="true" tabindex="-1"></a><span class="co"># True.</span></span>
|
||||
<span id="cb1-1368"><a href="#cb1-1368" 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="cb1-1369"><a href="#cb1-1369" aria-hidden="true" tabindex="-1"></a><span class="co"># Dictionary for additional configuration settings, see the doc for more details.</span></span>
|
||||
<span id="cb1-1370"><a href="#cb1-1370" 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="cb1-1371"><a href="#cb1-1371" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1372"><a href="#cb1-1372" aria-hidden="true" tabindex="-1"></a><span class="fu">use_trackio</span><span class="kw">:</span><span class="at"> bool | None</span></span>
|
||||
<span id="cb1-1373"><a href="#cb1-1373" aria-hidden="true" tabindex="-1"></a><span class="co"># Your trackio project name</span></span>
|
||||
<span id="cb1-1374"><a href="#cb1-1374" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_project_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1375"><a href="#cb1-1375" aria-hidden="true" tabindex="-1"></a><span class="co"># Set the name of your trackio run</span></span>
|
||||
<span id="cb1-1376"><a href="#cb1-1376" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_run_name</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1377"><a href="#cb1-1377" aria-hidden="true" tabindex="-1"></a><span class="co"># Hugging Face Space ID to sync dashboard to (optional, runs locally if not provided)</span></span>
|
||||
<span id="cb1-1378"><a href="#cb1-1378" aria-hidden="true" tabindex="-1"></a><span class="fu">trackio_space_id</span><span class="kw">:</span><span class="at"> str | None</span></span>
|
||||
<span id="cb1-1379"><a href="#cb1-1379" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1380"><a href="#cb1-1380" aria-hidden="true" tabindex="-1"></a><span class="co"># Enable OpenTelemetry metrics collection and Prometheus export</span></span>
|
||||
<span id="cb1-1381"><a href="#cb1-1381" aria-hidden="true" tabindex="-1"></a><span class="fu">use_otel_metrics</span><span class="kw">:</span><span class="at"> bool | None = False</span></span>
|
||||
<span id="cb1-1382"><a href="#cb1-1382" aria-hidden="true" tabindex="-1"></a><span class="co"># Host to bind the OpenTelemetry metrics server to</span></span>
|
||||
<span id="cb1-1383"><a href="#cb1-1383" aria-hidden="true" tabindex="-1"></a><span class="fu">otel_metrics_host</span><span class="kw">:</span><span class="at"> str | None = localhost</span></span>
|
||||
<span id="cb1-1384"><a href="#cb1-1384" aria-hidden="true" tabindex="-1"></a><span class="co"># Port for the Prometheus metrics HTTP server</span></span>
|
||||
<span id="cb1-1385"><a href="#cb1-1385" aria-hidden="true" tabindex="-1"></a><span class="fu">otel_metrics_port</span><span class="kw">:</span><span class="at"> int | None = 8000</span></span>
|
||||
<span id="cb1-1386"><a href="#cb1-1386" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1387"><a href="#cb1-1387" aria-hidden="true" tabindex="-1"></a><span class="co"># the number of activate layers in LISA</span></span>
|
||||
<span id="cb1-1388"><a href="#cb1-1388" 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="cb1-1389"><a href="#cb1-1389" aria-hidden="true" tabindex="-1"></a><span class="co"># how often to switch layers in LISA</span></span>
|
||||
<span id="cb1-1390"><a href="#cb1-1390" 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="cb1-1391"><a href="#cb1-1391" aria-hidden="true" tabindex="-1"></a><span class="co"># path under the model to access the layers</span></span>
|
||||
<span id="cb1-1392"><a href="#cb1-1392" 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="cb1-1393"><a href="#cb1-1393" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1394"><a href="#cb1-1394" 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="cb1-1395"><a href="#cb1-1395" 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="cb1-1396"><a href="#cb1-1396" 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="cb1-1397"><a href="#cb1-1397" 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="cb1-1398"><a href="#cb1-1398" 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="cb1-1399"><a href="#cb1-1399" 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="cb1-1400"><a href="#cb1-1400" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1401"><a href="#cb1-1401" 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="cb1-1402"><a href="#cb1-1402" 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="cb1-1403"><a href="#cb1-1403" 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="cb1-1404"><a href="#cb1-1404" 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="cb1-1405"><a href="#cb1-1405" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1406"><a href="#cb1-1406" 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="cb1-1407"><a href="#cb1-1407" 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="cb1-1408"><a href="#cb1-1408" aria-hidden="true" tabindex="-1"></a><span class="co"># preprocessor.size, otherwise, images won't be resized.</span></span>
|
||||
<span id="cb1-1409"><a href="#cb1-1409" 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="cb1-1410"><a href="#cb1-1410" 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="cb1-1411"><a href="#cb1-1411" aria-hidden="true" tabindex="-1"></a><span class="co"># to PIL.Image.Resampling for more details.</span></span>
|
||||
<span id="cb1-1412"><a href="#cb1-1412" 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="cb1-1413"><a href="#cb1-1413" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1414"><a href="#cb1-1414" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides to the base model configuration</span></span>
|
||||
<span id="cb1-1415"><a href="#cb1-1415" 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="cb1-1416"><a href="#cb1-1416" aria-hidden="true" tabindex="-1"></a><span class="co"># optional overrides the base model loading from_pretrained</span></span>
|
||||
<span id="cb1-1417"><a href="#cb1-1417" 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="cb1-1418"><a href="#cb1-1418" 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="cb1-1419"><a href="#cb1-1419" aria-hidden="true" tabindex="-1"></a><span class="co"># choice too</span></span>
|
||||
<span id="cb1-1420"><a href="#cb1-1420" 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="cb1-1421"><a href="#cb1-1421" 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="cb1-1422"><a href="#cb1-1422" 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="cb1-1423"><a href="#cb1-1423" aria-hidden="true" tabindex="-1"></a></span>
|
||||
<span id="cb1-1424"><a href="#cb1-1424" 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="cb1-1425"><a href="#cb1-1425" 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="cb1-1426"><a href="#cb1-1426" 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="cb1-1427"><a href="#cb1-1427" 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="cb1-1428"><a href="#cb1-1428" aria-hidden="true" tabindex="-1"></a><span class="fu">evaluation_strategy</span><span class="kw">:</span><span class="at"> str | None</span></span></code></pre></div><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></div>
|
||||
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user