Fix transformers 4.57.1 (#3473)
* Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * custom_datatype * recheck * Float16 * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Bug fix * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * torch_dtype * Update rl.py * Fix CE Loss * Versioning * Update loader.py * Update loader.py * extract_model_type_from_config * Model types * Update loader.py * get_transformers_model_type * Update loader.py * Update loader.py * Update loader.py * Update rl.py * Update pyproject.toml * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Versioning * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update vision.py * Update vision.py * Fix DataParallel * Update _utils.py * Update rl.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update mapper.py * Versioning * Update loader.py * Update loader.py * Update rl.py * Versioning * Update _utils.py * Fix auto_mapping * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Message * Update vision.py * Update loader.py * Update vision.py * cache_implementation * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Save max_seq_length * Update _utils.py * Update rl.py * Update vision.py * Update llama.py * Mistral3 vllm (#3349) * [WIP] use vLLM for vision language models * Update README.md Editing icon sizes * Update README.md Updating icon sizes * Update README.md (#2885) * MoE kernels AGPLv3 * versioning * Many bug fixes (#2908) * add deepseek v3 * add deepseek r1 base * add deepseek r1 zero * add deepseek distill llama * add deepseek distill models * remove redundant code when constructing model names * add mistral small to registry * rename model registration methods * rename deepseek registration methods * refactor naming for mistral and phi * add global register models * refactor model registration tests for new registry apis * add model search method * remove deprecated registration api * add quant type test * add registry readme * make llama registration more specific * clear registry when executing individual model registration file * more registry readme updates * Update _auto_install.py * Llama4 * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Synthetic data * Update mapper.py * Xet and Synthetic * Update synthetic.py * Update loader.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py --------- Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> * silienty skip falcon h1 import is transformers_version < 4.53.0 (#2912) * Dynamically adjust get_per_token_logps function and patch as well (#2911) * add intel gpu with vllm support (#2903) * [bugs] fix for casual mask (#2868) * fix for casual mask * use un_casual in sdpa * add missing mask * fix for type * Explicitly check if xformers exists for attention (#2889) * Update __init__.py * Update llama.py * if mlp doesn't exist in layer module check for feed_forward name for falcon h1 (#2913) * Move inputs to right devices. (#2919) * Move tensors to right devices * fix multi gpu for non mistral models * multi GPU RoPE for gemma2 * Finish up multi GPU inference * Make multiGPU rope a list * Remove unnecessary transfer to CPU * Remove unnecessary move to CPU * Donot move inputs to device yet will be handled separately in another PR * Move inputs to appropriate decoder device * Make device count global variable * Cleanup RoPE device code * Fixup num_gpu to device count * Cleanup device counts * Use device index for RoPE get_cache * Donot typecast * Use tuple instead of list for tensors. Use device index directly * fixup move to device logic * WIP VLM vLLM * Make vLLM patch a function * Add save and load lora functions * Make fast_inference setup depend on the flag * Improve fast inference patching mechanism * Make vision setting depend on checks in fastbasemodel * Check LoRA and vLLM intercompatibility for vision models * Comment pointing to vLLM LoRA check * Improve lora validation on vLLM * Error out on no vLLM and increase max lora rank * Bug fixes (#3017) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit4021da634a. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * fix for casual mask (#3011) * [intel] add for intel path for llama.py (#3012) * fix for intel path * remove unuse code * Update unsloth/models/llama.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update llama.py * Fix Gemma 2 (#3024) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit4021da634a. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * falcon force float32 on sm<75 machines (#3026) * Fix torch compile issues (#3028) * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update pyproject.toml * Delete .gitignore * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update _utils.py * Update pyproject.toml * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update chat_templates.py * Seasame force float16 / float32 * Fix Seasame * Update loader.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * is_multimodal * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update vision.py * Update vision.py * Update vision.py * UNSLOTH_DISABLE_STATIC_GENERATION * Update vision.py * Auto vision detection * Sesame * Whisper * Update loader.py * Update loader.py * Update loader.py * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update loader.py * Update loader.py * Update loader.py * Update loader.py * Update _utils.py * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update rl.py * logging * Update pyproject.toml * Update rl.py * versioning * Update rl.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * logits / temperature * Update rl_replacements.py * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Debugging only * Update llama.py * Update llama.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Generic efficient GRPO * Update rl_replacements.py * Update rl_replacements.py * Remove debugging * Update rl_replacements.py * Update rl_replacements.py * Update vision.py * Update llama.py * Update rl_replacements.py * versioning * Update _utils.py * Update vision.py * Update mapper.py * Update loader.py * Update mapper.py * Update vision.py * Update loader.py * Update vision.py * Update loader.py * Update _utils.py * Update vision.py * gradient checkpointing * Gemma 3N fixes * Update loader.py * Versioning * Gemma 3N fixes * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Fix setup.py * setup.py * Prints * Update setup.py * Update setup.py * Update setup.py * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update pyproject.toml * Update vision.py * Update vision.py * Update pyproject.toml * Update vision.py * Update _utils.py * Update __init__.py * Update __init__.py * Small fixes * Update vision.py * Update vision.py * versioning * Update __init__.py * Update llama.py * Update rl.py * Update rl.py * Update _utils.py * Update vision.py * Update vision.py * compiler stance * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Update rl_replacements.py * Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990) This reverts commit4021da634a. * skip_guard_eval_unsafe fix * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update synthetic.py * Update llama.py * Update llama.py * Fix `quantization_method` * versioning * Update _utils.py * Update _utils.py * Update _utils.py * check stride * Cleanup * Update rope_embedding.py * Update gemma2.py * Fix `set_stance` * Update pyproject.toml * Update _utils.py * Fixup patch vllm * Disable mllama * Use variables to decide VLM support * Better attn_impl handling * Patch TF protobuf incompatability * Torch 2.8 (#3186) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update _auto_install.py * Update pyproject.toml * Update rl.py * Protobuf issue * Update pyproject.toml * Fix extras transformers typo in pyproject.toml * Update _utils.py * Bug fixes (#3195) * Fix mamba * Update loader.py * Update vision.py * Update loader.py * Filter vLLM standby logs (#3131) * filter vLLM standby logs * safeguard standby logger patch * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py * Update unsloth/models/_utils.py --------- Co-authored-by: Daniel Han <danielhanchen@gmail.com> * Update loader.py * Add scaler * Update llama.py * Update _utils.py * Versioning * GPT OSS fix * GPT OSS fix * Update loader.py * Update vision.py * Update vision.py * Update loader.py * Update vision.py * Update vision.py * Update llama.py * Update llama.py * Update llama.py * Versioning * Update mapper.py * Update vision.py * Update vision.py * Update vision.py * Upcast norms * Update loader.py * Update vision.py * Upcast layernorms * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update llama.py * Update save.py * Update rl.py * Update pyproject.toml * Update rl.py * Update rl_replacements.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Update __init__.py * Torch 2.8 * Update rl_replacements.py * Update loader.py * UNSLOTH_ENABLE_CCE * Fix * Update loader.py * Update loader.py * Update __init__.py * Update __init__.py * Update __init__.py * Update __init__.py * Import fixes * Update loader.py * Fix aimv2 issue * Update loader.py * Update import_fixes.py * Update import_fixes.py * Update loader.py * Update loader.py * Update loader.py * Upgrade * Update loader.py * Update loader.py * Update loader.py * Update loader.py --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * adallow float32 dtype in FastLanguageModel (#3204) * Update loader.py * Update vision.py * Suppress message and use unsloth sampling params * Use trl sampling params for now * Improve error message * fixup quantized fast inference model name * Add mistral 3 support --------- Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: Daniel Han <danielhanchen@gmail.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com> * Set padding to 0 * Fix patch * fixup patch (#3359) Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> * Update vision.py * Versioning * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * MXFP4 dequant * Update loader.py * Update vision.py * load_in_16bit * Update vision.py * Update vision.py * Update vision.py * Update rl.py * Update vision.py * offload_embedding * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update rl_replacements.py * Update loader.py * Fix padding issue * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * Update vision.py * New models * Update llama.py * Versioning * Update _utils.py * Update llama.py * Update _utils.py * Update llama.py * Fix AMD * Update _utils.py * Update llama.py * Update vision.py * DEVICE_TYPE_TORCH * Update __init__.py * Update __init__.py * Update _utils.py * Move DEVICE_TYPE * Update rl_replacements.py * Update loader.py * AMD install script * Move AMD * Update _amd_install.sh * Update pyproject.toml --------- Co-authored-by: Datta Nimmaturi <venkatadattasainimmaturi@gmail.com> Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com> Co-authored-by: jeromeku <jerome.ku@gmail.com> Co-authored-by: DoubleMathew <mmathew23@gmail.com> Co-authored-by: Lei Zhenyuan <zhenyuan.lei@intel.com> Co-authored-by: parth2510 <parthguptapg7326@gmail.com>
This commit is contained in:
Daniel Han
GitHub
parent
77b5256f71
commit
cb8484eaf1
10 changed files with 237 additions and 56 deletions
|
|
@ -39,11 +39,10 @@ triton = [
|
|||
"triton>=3.0.0 ; ('linux' in sys_platform)",
|
||||
"triton-windows ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
|
||||
]
|
||||
huggingface = [
|
||||
"unsloth_zoo>=2025.10.4",
|
||||
huggingfacenotorch = [
|
||||
"unsloth_zoo>=2025.10.5",
|
||||
"wheel>=0.42.0",
|
||||
"packaging",
|
||||
"torchvision",
|
||||
"numpy",
|
||||
"tqdm",
|
||||
"psutil",
|
||||
|
|
@ -58,6 +57,10 @@ huggingface = [
|
|||
"diffusers",
|
||||
"transformers>=4.51.3,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3,!=4.53.0,!=4.54.0,!=4.55.0,!=4.55.1,<=4.56.2",
|
||||
"trl>=0.7.9,!=0.9.0,!=0.9.1,!=0.9.2,!=0.9.3,!=0.15.0,!=0.19.0,<=0.23.0",
|
||||
]
|
||||
huggingface = [
|
||||
"unsloth[huggingfacenotorch]",
|
||||
"torchvision",
|
||||
"unsloth[triton]",
|
||||
]
|
||||
windows = [
|
||||
|
|
@ -458,7 +461,7 @@ colab-ampere-torch220 = [
|
|||
"flash-attn>=2.6.3 ; ('linux' in sys_platform)",
|
||||
]
|
||||
colab-new = [
|
||||
"unsloth_zoo>=2025.10.4",
|
||||
"unsloth_zoo>=2025.10.5",
|
||||
"packaging",
|
||||
"tyro",
|
||||
"transformers>=4.51.3,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3,!=4.53.0,!=4.54.0,!=4.55.0,!=4.55.1,<=4.56.2",
|
||||
|
|
@ -740,7 +743,12 @@ intel-gpu-torch270 = [
|
|||
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp312-cp312-linux_x86_64.whl#sha256=c806d44aa2ca5d225629f6fbc6c994d5deaac2d2cde449195bc8e3522ddd219a ; ('linux' in sys_platform) and python_version == '3.12' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
|
||||
"torch @ https://download.pytorch.org/whl/xpu/torch-2.7.0%2Bxpu-cp313-cp313-linux_x86_64.whl#sha256=25d8277b7f01d42e2e014ccbab57a2692b6ec4eff8dcf894eda1b297407cf97a ; ('linux' in sys_platform) and python_version == '3.13' and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
|
||||
]
|
||||
|
||||
amd = [
|
||||
"unsloth[huggingfacenotorch]",
|
||||
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-manylinux_2_24_x86_64.whl ; ('linux' in sys_platform) and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
|
||||
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-win_amd64.whl ; (sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
|
||||
"bitsandbytes @ https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-manylinux_2_24_aarch64.whl ; ('linux' in sys_platform) and (platform_machine == 'aarch64')",
|
||||
]
|
||||
[project.urls]
|
||||
homepage = "http://www.unsloth.ai"
|
||||
documentation = "https://github.com/unslothai/unsloth"
|
||||
|
|
|
|||
|
|
@ -69,49 +69,14 @@ except Exception as exception:
|
|||
raise exception
|
||||
pass
|
||||
|
||||
@functools.cache
|
||||
def is_hip():
|
||||
return bool(getattr(getattr(torch, "version", None), "hip", None))
|
||||
pass
|
||||
|
||||
@functools.cache
|
||||
def get_device_type():
|
||||
if hasattr(torch, "cuda") and torch.cuda.is_available():
|
||||
if is_hip():
|
||||
return "hip"
|
||||
return "cuda"
|
||||
elif hasattr(torch, "xpu") and torch.xpu.is_available():
|
||||
return "xpu"
|
||||
# Check torch.accelerator
|
||||
if hasattr(torch, "accelerator"):
|
||||
if not torch.accelerator.is_available():
|
||||
raise NotImplementedError("Unsloth cannot find any torch accelerator? You need a GPU.")
|
||||
accelerator = str(torch.accelerator.current_accelerator())
|
||||
if accelerator in ("cuda", "xpu", "hip"):
|
||||
raise RuntimeError(
|
||||
f"Unsloth: Weirdly `torch.cuda.is_available()`, `torch.xpu.is_available()` and `is_hip` all failed.\n"\
|
||||
f"But `torch.accelerator.current_accelerator()` works with it being = `{accelerator}`\n"\
|
||||
f"Please reinstall torch - it's most likely broken :("
|
||||
)
|
||||
raise NotImplementedError("Unsloth currently only works on NVIDIA, AMD and Intel GPUs.")
|
||||
pass
|
||||
DEVICE_TYPE : str = get_device_type()
|
||||
# HIP fails for autocast and other torch functions. Use CUDA instead
|
||||
DEVICE_TYPE_TORCH = DEVICE_TYPE
|
||||
if DEVICE_TYPE_TORCH == "hip": DEVICE_TYPE_TORCH = "cuda"
|
||||
|
||||
@functools.cache
|
||||
def get_device_count():
|
||||
if DEVICE_TYPE in ("cuda", "hip"):
|
||||
return torch.cuda.device_count()
|
||||
elif DEVICE_TYPE == "xpu":
|
||||
return torch.xpu.device_count()
|
||||
else:
|
||||
return 1
|
||||
pass
|
||||
|
||||
DEVICE_COUNT : int = get_device_count()
|
||||
|
||||
from .device_type import (
|
||||
is_hip,
|
||||
get_device_type,
|
||||
DEVICE_TYPE,
|
||||
DEVICE_TYPE_TORCH,
|
||||
DEVICE_COUNT,
|
||||
ALLOW_PREQUANTIZED_MODELS,
|
||||
)
|
||||
# Reduce VRAM usage by reducing fragmentation
|
||||
# And optimize pinning of memory
|
||||
# TODO(billishyahao): need to add hip related optimization...
|
||||
|
|
@ -201,7 +166,10 @@ if DEVICE_TYPE == "cuda":
|
|||
else: from triton.common.build import libcuda_dirs
|
||||
|
||||
# Try loading bitsandbytes and triton
|
||||
import bitsandbytes as bnb
|
||||
try:
|
||||
import bitsandbytes as bnb
|
||||
except:
|
||||
print("Unsloth: `bitsandbytes` is not installed - 4bit QLoRA unallowed, but 16bit and full finetuning works!")
|
||||
try:
|
||||
cdequantize_blockwise_fp32 = bnb.functional.lib.cdequantize_blockwise_fp32
|
||||
libcuda_dirs()
|
||||
|
|
|
|||
32
unsloth/_amd_install.sh
Normal file
32
unsloth/_amd_install.sh
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
#!/usr/bin/env bash
|
||||
# _amd_install.sh
|
||||
# Non-interactive installer: build tools, PyTorch (ROCm 6.4), bitsandbytes (HIP), and Unsloth from source.
|
||||
# Usage:
|
||||
# bash _amd_install.sh
|
||||
#
|
||||
|
||||
set -euo pipefail
|
||||
export DEBIAN_FRONTEND=noninteractive
|
||||
|
||||
apt-get update
|
||||
apt-get install -y --no-install-recommends build-essential cmake git
|
||||
|
||||
pip install \
|
||||
torch==2.8.0 torchvision torchaudio torchao==0.13.0 xformers \
|
||||
--index-url https://download.pytorch.org/whl/rocm6.4
|
||||
|
||||
WORKDIR="$(pwd)"
|
||||
TMPDIR="$(mktemp -d)"
|
||||
cd "$TMPDIR"
|
||||
git clone https://github.com/bitsandbytes-foundation/bitsandbytes.git
|
||||
cd bitsandbytes
|
||||
arch
|
||||
cmake -DCOMPUTE_BACKEND=hip -S .
|
||||
make -j"$(nproc)"
|
||||
pip install .
|
||||
cd "$WORKDIR"
|
||||
rm -rf "$TMPDIR"
|
||||
|
||||
pip install --no-deps unsloth unsloth-zoo
|
||||
pip install "unsloth_zoo[base] @ git+https://github.com/unslothai/unsloth-zoo"
|
||||
pip install "unsloth[base] @ git+https://github.com/unslothai/unsloth"
|
||||
80
unsloth/device_type.py
Normal file
80
unsloth/device_type.py
Normal file
|
|
@ -0,0 +1,80 @@
|
|||
# Copyright 2023-present Daniel Han-Chen & the Unsloth team. All rights reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
__all__ = [
|
||||
"is_hip",
|
||||
"get_device_type",
|
||||
"DEVICE_TYPE",
|
||||
"DEVICE_TYPE_TORCH",
|
||||
"DEVICE_COUNT",
|
||||
"ALLOW_PREQUANTIZED_MODELS",
|
||||
]
|
||||
|
||||
import torch
|
||||
import functools
|
||||
|
||||
@functools.cache
|
||||
def is_hip():
|
||||
return bool(getattr(getattr(torch, "version", None), "hip", None))
|
||||
pass
|
||||
|
||||
@functools.cache
|
||||
def get_device_type():
|
||||
if hasattr(torch, "cuda") and torch.cuda.is_available():
|
||||
if is_hip():
|
||||
return "hip"
|
||||
return "cuda"
|
||||
elif hasattr(torch, "xpu") and torch.xpu.is_available():
|
||||
return "xpu"
|
||||
# Check torch.accelerator
|
||||
if hasattr(torch, "accelerator"):
|
||||
if not torch.accelerator.is_available():
|
||||
raise NotImplementedError("Unsloth cannot find any torch accelerator? You need a GPU.")
|
||||
accelerator = str(torch.accelerator.current_accelerator())
|
||||
if accelerator in ("cuda", "xpu", "hip"):
|
||||
raise RuntimeError(
|
||||
f"Unsloth: Weirdly `torch.cuda.is_available()`, `torch.xpu.is_available()` and `is_hip` all failed.\n"\
|
||||
f"But `torch.accelerator.current_accelerator()` works with it being = `{accelerator}`\n"\
|
||||
f"Please reinstall torch - it's most likely broken :("
|
||||
)
|
||||
raise NotImplementedError("Unsloth currently only works on NVIDIA, AMD and Intel GPUs.")
|
||||
pass
|
||||
DEVICE_TYPE : str = get_device_type()
|
||||
# HIP fails for autocast and other torch functions. Use CUDA instead
|
||||
DEVICE_TYPE_TORCH = DEVICE_TYPE
|
||||
if DEVICE_TYPE_TORCH == "hip": DEVICE_TYPE_TORCH = "cuda"
|
||||
|
||||
@functools.cache
|
||||
def get_device_count():
|
||||
if DEVICE_TYPE in ("cuda", "hip"):
|
||||
return torch.cuda.device_count()
|
||||
elif DEVICE_TYPE == "xpu":
|
||||
return torch.xpu.device_count()
|
||||
else:
|
||||
return 1
|
||||
pass
|
||||
|
||||
DEVICE_COUNT : int = get_device_count()
|
||||
|
||||
# Check blocksize for 4bit -> 64 for CUDA, 128 for AMD
|
||||
# If AMD, we cannot load pre-quantized models for now :(
|
||||
ALLOW_PREQUANTIZED_MODELS : bool = True
|
||||
if DEVICE_TYPE == "hip":
|
||||
try:
|
||||
from bitsandbytes.nn.modules import Params4bit
|
||||
if "blocksize = 64 if not HIP_ENVIRONMENT else 128" in inspect.getsource(Params4bit):
|
||||
ALLOW_PREQUANTIZED_MODELS = False
|
||||
except:
|
||||
pass
|
||||
pass
|
||||
|
|
@ -19,7 +19,14 @@ next_power_of_2 = triton.next_power_of_2
|
|||
import functools
|
||||
from typing import Optional
|
||||
|
||||
from .. import DEVICE_TYPE, DEVICE_COUNT
|
||||
from ..device_type import (
|
||||
is_hip,
|
||||
get_device_type,
|
||||
DEVICE_TYPE,
|
||||
DEVICE_TYPE_TORCH,
|
||||
DEVICE_COUNT,
|
||||
ALLOW_PREQUANTIZED_MODELS,
|
||||
)
|
||||
from .fp8 import weight_dequant, fp8_linear
|
||||
|
||||
# torch.cuda.amp.custom_fwd is deprecated >= 2.4
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@
|
|||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
__version__ = "2025.10.4"
|
||||
__version__ = "2025.10.5"
|
||||
|
||||
__all__ = [
|
||||
"SUPPORTS_BFLOAT16",
|
||||
|
|
@ -87,7 +87,14 @@ import functools
|
|||
import warnings, subprocess, re, inspect, psutil, os, math
|
||||
from unsloth_zoo.utils import Version
|
||||
from importlib.metadata import version as importlib_version
|
||||
from unsloth import DEVICE_TYPE, DEVICE_COUNT, DEVICE_TYPE_TORCH
|
||||
from ..device_type import (
|
||||
is_hip,
|
||||
get_device_type,
|
||||
DEVICE_TYPE,
|
||||
DEVICE_TYPE_TORCH,
|
||||
DEVICE_COUNT,
|
||||
ALLOW_PREQUANTIZED_MODELS,
|
||||
)
|
||||
from unsloth_zoo.log import logger
|
||||
from unsloth_zoo.tokenizer_utils import (
|
||||
patch_tokenizer as _patch_tokenizer,
|
||||
|
|
@ -1331,6 +1338,7 @@ pass
|
|||
|
||||
def patch_gradient_accumulation_fix(Trainer):
|
||||
# Fixes gradient accumulation
|
||||
# Fixes Output 0 of UnslothFusedLossBackward is a view and is being modified inplace.
|
||||
import inspect
|
||||
if hasattr(Trainer, "get_batch_samples"):
|
||||
if Trainer.get_batch_samples.__name__ == "_unsloth_get_batch_samples": return
|
||||
|
|
@ -1346,6 +1354,32 @@ def patch_gradient_accumulation_fix(Trainer):
|
|||
|
||||
# Also fix passing in num_items_in_batch
|
||||
if not hasattr(Trainer, "_old_compute_loss"):
|
||||
|
||||
# Fix transformers 4.57.0 causing `Output 0 of UnslothFusedLossBackward is a view and is being modified inplace.`
|
||||
function = inspect.getsource(Trainer.compute_loss)
|
||||
if "loss *=" in function or "loss*=" in function:
|
||||
where = function.find("def")
|
||||
function = function.split("\n")
|
||||
function = "\n".join(x[where:] for x in function)
|
||||
|
||||
# Import all variables that need importing
|
||||
import transformers.trainer
|
||||
items_in_trainer = dir(transformers.trainer)
|
||||
good_items = []
|
||||
for item in items_in_trainer:
|
||||
if item in function: good_items.append(item)
|
||||
pass
|
||||
exec("from transformers.trainer import (" + ", ".join(x for x in good_items) + ")", globals())
|
||||
|
||||
# Replace loss*= with loss = loss *
|
||||
function = re.sub(
|
||||
r"loss[\s]{0,}\*\=",
|
||||
"loss = loss *",
|
||||
function,
|
||||
)
|
||||
exec(function, globals())
|
||||
Trainer.compute_loss = compute_loss
|
||||
pass
|
||||
Trainer._old_compute_loss = Trainer.compute_loss
|
||||
Trainer.compute_loss = _unsloth_pre_compute_loss
|
||||
pass
|
||||
|
|
|
|||
|
|
@ -27,7 +27,14 @@ from transformers import __version__ as transformers_version
|
|||
from unsloth_zoo.utils import Version, _get_dtype
|
||||
from unsloth_zoo.hf_utils import dtype_from_config, add_dtype_kwargs, fix_lora_auto_mapping
|
||||
from unsloth_zoo.peft_utils import SKIP_QUANTIZATION_MODULES
|
||||
from unsloth import DEVICE_TYPE, DEVICE_COUNT, DEVICE_TYPE_TORCH
|
||||
from ..device_type import (
|
||||
is_hip,
|
||||
get_device_type,
|
||||
DEVICE_TYPE,
|
||||
DEVICE_TYPE_TORCH,
|
||||
DEVICE_COUNT,
|
||||
ALLOW_PREQUANTIZED_MODELS,
|
||||
)
|
||||
|
||||
transformers_version = Version(transformers_version)
|
||||
# Transformers moved rotary embeddings out of all attention layers
|
||||
|
|
|
|||
|
|
@ -45,6 +45,14 @@ except:
|
|||
pass
|
||||
from huggingface_hub import HfFileSystem
|
||||
import importlib.util
|
||||
from ..device_type import (
|
||||
is_hip,
|
||||
get_device_type,
|
||||
DEVICE_TYPE,
|
||||
DEVICE_TYPE_TORCH,
|
||||
DEVICE_COUNT,
|
||||
ALLOW_PREQUANTIZED_MODELS,
|
||||
)
|
||||
|
||||
# https://github.com/huggingface/transformers/pull/26037 allows 4 bit loading!
|
||||
from unsloth_zoo.utils import Version, _get_dtype
|
||||
|
|
@ -195,6 +203,12 @@ class FastLanguageModel(FastLlamaModel):
|
|||
old_model_name = model_name
|
||||
if not use_exact_model_name:
|
||||
model_name = get_model_name(model_name, load_in_4bit)
|
||||
# Check if pre-quantized models are allowed
|
||||
# For eg AMD GPUs need blocksize = 128, but our pre-quants are blocksize = 64
|
||||
if not ALLOW_PREQUANTIZED_MODELS and model_name.endswith(("-unsloth-bnb-4bit", "-bnb-4bit")):
|
||||
model_name = model_name.removesuffix("-unsloth-bnb-4bit")
|
||||
model_name = model_name.removesuffix("-bnb-4bit")
|
||||
pass
|
||||
|
||||
if USE_MODELSCOPE and not os.path.exists(model_name):
|
||||
from modelscope import snapshot_download
|
||||
|
|
@ -306,6 +320,12 @@ class FastLanguageModel(FastLlamaModel):
|
|||
model_name = peft_config.base_model_name_or_path
|
||||
if not use_exact_model_name:
|
||||
model_name = get_model_name(model_name, load_in_4bit)
|
||||
# Check if pre-quantized models are allowed
|
||||
# For eg AMD GPUs need blocksize = 128, but our pre-quants are blocksize = 64
|
||||
if not ALLOW_PREQUANTIZED_MODELS and model_name.endswith(("-unsloth-bnb-4bit", "-bnb-4bit")):
|
||||
model_name = model_name.removesuffix("-unsloth-bnb-4bit")
|
||||
model_name = model_name.removesuffix("-bnb-4bit")
|
||||
pass
|
||||
model_config = AutoConfig.from_pretrained(
|
||||
model_name,
|
||||
token = token,
|
||||
|
|
@ -618,6 +638,12 @@ class FastModel(FastBaseModel):
|
|||
old_model_name = model_name
|
||||
if not use_exact_model_name:
|
||||
model_name = get_model_name(model_name, load_in_4bit)
|
||||
# Check if pre-quantized models are allowed
|
||||
# For eg AMD GPUs need blocksize = 128, but our pre-quants are blocksize = 64
|
||||
if not ALLOW_PREQUANTIZED_MODELS and model_name.endswith(("-unsloth-bnb-4bit", "-bnb-4bit")):
|
||||
model_name = model_name.removesuffix("-unsloth-bnb-4bit")
|
||||
model_name = model_name.removesuffix("-bnb-4bit")
|
||||
pass
|
||||
|
||||
# Check modelscope
|
||||
if USE_MODELSCOPE and not os.path.exists(model_name):
|
||||
|
|
@ -833,7 +859,12 @@ class FastModel(FastBaseModel):
|
|||
model_name = peft_config.base_model_name_or_path
|
||||
if not use_exact_model_name:
|
||||
model_name = get_model_name(model_name, load_in_4bit)
|
||||
|
||||
# Check if pre-quantized models are allowed
|
||||
# For eg AMD GPUs need blocksize = 128, but our pre-quants are blocksize = 64
|
||||
if not ALLOW_PREQUANTIZED_MODELS and model_name.endswith(("-unsloth-bnb-4bit", "-bnb-4bit")):
|
||||
model_name = model_name.removesuffix("-unsloth-bnb-4bit")
|
||||
model_name = model_name.removesuffix("-bnb-4bit")
|
||||
pass
|
||||
model_config = AutoConfig.from_pretrained(
|
||||
model_name,
|
||||
token = token,
|
||||
|
|
|
|||
|
|
@ -26,7 +26,14 @@ import torch
|
|||
import inspect
|
||||
from collections import defaultdict
|
||||
from unsloth_zoo.rl_replacements import RL_REPLACEMENTS, left_pack_padding
|
||||
from unsloth import DEVICE_TYPE
|
||||
from ..device_type import (
|
||||
is_hip,
|
||||
get_device_type,
|
||||
DEVICE_TYPE,
|
||||
DEVICE_TYPE_TORCH,
|
||||
DEVICE_COUNT,
|
||||
ALLOW_PREQUANTIZED_MODELS,
|
||||
)
|
||||
import textwrap
|
||||
|
||||
RL_EXTRA_ARGS = defaultdict(list)
|
||||
|
|
|
|||
|
|
@ -71,7 +71,14 @@ except:
|
|||
# Old HF Hub versions <= 0.0.25
|
||||
from huggingface_hub.utils._token import get_token
|
||||
pass
|
||||
from unsloth import DEVICE_TYPE, DEVICE_COUNT, DEVICE_TYPE_TORCH
|
||||
from ..device_type import (
|
||||
is_hip,
|
||||
get_device_type,
|
||||
DEVICE_TYPE,
|
||||
DEVICE_TYPE_TORCH,
|
||||
DEVICE_COUNT,
|
||||
ALLOW_PREQUANTIZED_MODELS,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"FastBaseModel",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue