mirror of
https://github.com/unslothai/unsloth
synced 2026-04-21 13:37:39 +00:00
Bug fixes (#3546)
* 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 * Update pyproject.toml * Delete _amd_install.sh * Update device_type.py * Update loader.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update _utils.py * Update tokenizer_utils.py * Versioning * Update pyproject.toml * Update loader.py * Update _utils.py * Update pyproject.toml * Update pyproject.toml * Update _utils.py * Update pyproject.toml * Update _utils.py * Update _utils.py * Update loader.py * Update _utils.py * Update _utils.py * local_files_only * Cut Cross Entropy * Update llama.py * Update vision.py * Update vision.py * Update vision.py * Qwen 3 VL vLLM (#3489) * Update __init__.py * patch_torchao * torchao_logger * Update rl_replacements.py * Fix * Update rl.py * Update rl.py * Update rl.py * Update rl.py * Update _utils.py * Versioning --------- 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
c449c7b06e
commit
a9ff4e23c9
6 changed files with 30 additions and 24 deletions
|
|
@ -55,11 +55,11 @@ huggingfacenotorch = [
|
|||
"hf_transfer",
|
||||
"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,!=4.57.0,<=4.57.2",
|
||||
"trl>=0.18.2,!=0.19.0,<=0.23.0",
|
||||
"trl>=0.18.2,!=0.19.0,<=0.24.0",
|
||||
]
|
||||
huggingface = [
|
||||
"unsloth[huggingfacenotorch]",
|
||||
"unsloth_zoo>=2025.10.13",
|
||||
"unsloth_zoo>=2025.11.1",
|
||||
"torchvision",
|
||||
"unsloth[triton]",
|
||||
]
|
||||
|
|
@ -489,7 +489,7 @@ colab-ampere-torch220 = [
|
|||
"flash-attn>=2.6.3 ; ('linux' in sys_platform)",
|
||||
]
|
||||
colab-new = [
|
||||
"unsloth_zoo>=2025.10.13",
|
||||
"unsloth_zoo>=2025.11.1",
|
||||
"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,!=4.57.0,<=4.57.2",
|
||||
|
|
@ -507,7 +507,7 @@ colab-new = [
|
|||
]
|
||||
colab-no-deps = [
|
||||
"accelerate>=0.34.1",
|
||||
"trl>=0.18.2,!=0.19.0,<=0.23.0",
|
||||
"trl>=0.18.2,!=0.19.0,<=0.24.0",
|
||||
"peft>=0.7.1",
|
||||
"xformers ; ('linux' in sys_platform or sys_platform == 'win32') and (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
|
||||
"bitsandbytes>=0.45.5,!=0.46.0,!=0.48.0",
|
||||
|
|
|
|||
|
|
@ -29,7 +29,6 @@ already_imported = [mod for mod in critical_modules if mod in sys.modules]
|
|||
# their code at import time. If they're imported first, the original (slower,
|
||||
# more memory-intensive) implementations will be used instead of Unsloth's
|
||||
# optimized versions, potentially causing OOM errors or slower training.
|
||||
|
||||
if already_imported:
|
||||
# stacklevel=2 makes warning point to user's import line rather than this library code,
|
||||
# showing them exactly where to fix the import order in their script
|
||||
|
|
@ -40,7 +39,7 @@ if already_imported:
|
|||
f"Please restructure your imports with 'import unsloth' at the top of your file.",
|
||||
stacklevel = 2,
|
||||
)
|
||||
pass
|
||||
del already_imported, critical_modules
|
||||
|
||||
# Unsloth currently does not work on multi GPU setups - sadly we are a 2 brother team so
|
||||
# enabling it will require much more work, so we have to prioritize. Please understand!
|
||||
|
|
@ -57,14 +56,12 @@ os.environ["PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION"] = "python"
|
|||
# Log Unsloth is being used
|
||||
os.environ["UNSLOTH_IS_PRESENT"] = "1"
|
||||
|
||||
import importlib.util
|
||||
from pathlib import Path
|
||||
from importlib.metadata import version as importlib_version
|
||||
from importlib.metadata import PackageNotFoundError
|
||||
# Check for unsloth_zoo
|
||||
try:
|
||||
unsloth_zoo_version = importlib_version("unsloth_zoo")
|
||||
if Version(unsloth_zoo_version) < Version("2025.10.13"):
|
||||
if Version(unsloth_zoo_version) < Version("2025.11.1"):
|
||||
print(
|
||||
"Unsloth: Please update Unsloth and Unsloth-Zoo to the latest version!\n"\
|
||||
"Do this via `pip install --upgrade --force-reinstall --no-cache-dir --no-deps unsloth unsloth_zoo`"
|
||||
|
|
@ -82,7 +79,7 @@ except PackageNotFoundError:
|
|||
raise ImportError(f"Unsloth: Please install unsloth_zoo via `pip install unsloth_zoo` then retry!")
|
||||
except:
|
||||
raise
|
||||
pass
|
||||
del PackageNotFoundError, importlib_version
|
||||
|
||||
# Try importing PyTorch and check version
|
||||
try:
|
||||
|
|
@ -92,8 +89,8 @@ except ModuleNotFoundError:
|
|||
"Unsloth: Pytorch is not installed. Go to https://pytorch.org/.\n"\
|
||||
"We have some installation instructions on our Github page."
|
||||
)
|
||||
except Exception as exception:
|
||||
raise exception
|
||||
except:
|
||||
raise
|
||||
pass
|
||||
|
||||
from unsloth_zoo.device_type import (
|
||||
|
|
@ -130,7 +127,7 @@ if DEVICE_TYPE == "cuda":
|
|||
else:
|
||||
def is_bf16_supported(): return SUPPORTS_BFLOAT16
|
||||
torch.cuda.is_bf16_supported = is_bf16_supported
|
||||
pass
|
||||
del major_version, minor_version
|
||||
elif DEVICE_TYPE == "hip":
|
||||
SUPPORTS_BFLOAT16 = torch.cuda.is_bf16_supported()
|
||||
elif DEVICE_TYPE == "xpu":
|
||||
|
|
@ -179,6 +176,8 @@ if DEVICE_TYPE == "cuda":
|
|||
latest_cuda = np.argsort([float(find_number.search(x).group(1)) for x in possible_cudas])[::-1][0]
|
||||
latest_cuda = possible_cudas[latest_cuda]
|
||||
os.system(f"ldconfig /usr/local/{latest_cuda}")
|
||||
del find_number, latest_cuda
|
||||
del possible_cudas, find_cuda
|
||||
pass
|
||||
|
||||
importlib.reload(bnb)
|
||||
|
|
@ -200,7 +199,7 @@ if DEVICE_TYPE == "cuda":
|
|||
"Also try `sudo ldconfig /usr/local/cuda-xx.x` - find the latest cuda version.\n"\
|
||||
"Unsloth will still run for now, but maybe it might crash - let's hope it works!"
|
||||
)
|
||||
pass
|
||||
del libcuda_dirs
|
||||
elif DEVICE_TYPE == "hip":
|
||||
# NO-OP for rocm device
|
||||
pass
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@
|
|||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
|
||||
__version__ = "2025.10.12"
|
||||
__version__ = "2025.11.1"
|
||||
|
||||
__all__ = [
|
||||
"SUPPORTS_BFLOAT16",
|
||||
|
|
@ -235,6 +235,9 @@ del transformers_training_args_logger
|
|||
# No label_names provided for model class
|
||||
from transformers.trainer import logger as transformers_trainer_logger
|
||||
transformers_trainer_logger.addFilter(HideLoggingMessage("No label_names"))
|
||||
|
||||
# The tokenizer has new PAD/BOS/EOS tokens that differ from the model config and generation config.
|
||||
transformers_trainer_logger.addFilter(HideLoggingMessage("The tokenizer has new"))
|
||||
del transformers_trainer_logger
|
||||
|
||||
# Using the default loss: `ForCausalLMLoss`.
|
||||
|
|
|
|||
|
|
@ -752,11 +752,11 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
|
|||
" scale_rewards = False\n"\
|
||||
"elif loss_type.lower() == 'dapo':\n"\
|
||||
" if mask_truncated_completions != True:\n"\
|
||||
" print('Unsloth: The DAPO paper recommends `mask_truncated_completions = True`')\n"\
|
||||
" print('Unsloth: The DAPO paper recommends `mask_truncated_completions = True` - we will set it.')\n"\
|
||||
" if epsilon_high != 0.28:\n"\
|
||||
" print('Unsloth: The DAPO paper recommends `epsilon_high = 0.28`')\n"\
|
||||
" print('Unsloth: The DAPO paper recommends `epsilon_high = 0.28` - we will set it.')\n"\
|
||||
" if beta != 0.0:\n"\
|
||||
" print('Unsloth: The DAPO paper recommends setting `beta = 0.0` to remove the KL term')\n"\
|
||||
" print('Unsloth: The DAPO paper recommends setting `beta = 0.0` to remove the KL term - we will set it.')\n"\
|
||||
" mask_truncated_completions = True\n"\
|
||||
" epsilon_high = 0.28\n"\
|
||||
" beta = 0.0\n"\
|
||||
|
|
@ -1085,10 +1085,13 @@ def patch_functions(RLTrainer, trainer_file, RLTrainer_name, all_imports, import
|
|||
)
|
||||
|
||||
# Replace self.llm.generate and self.llm.chat
|
||||
lora_name = trainer_file + "_lora_model"
|
||||
if "CUDA_VISIBLE_DEVICES" in os.environ:
|
||||
lora_name = trainer_file + "_lora_model_' + " + "(os.environ.get('CUDA_VISIBLE_DEVICES', '0').replace(',',''))"
|
||||
else:
|
||||
lora_name = trainer_file + "_lora_model'"
|
||||
source = re.sub(
|
||||
r"(self\.llm\.(?:generate|chat)\([^\)]{1,})\)",
|
||||
r"\1, lora_request = self.model.load_lora('" + lora_name + r"', load_tensors = True))",
|
||||
r"\1, lora_request = self.model.load_lora('" + lora_name + r", load_tensors = True))",
|
||||
source
|
||||
)
|
||||
# Prefer using unsloth's sampling params and fallback to trl's if not found
|
||||
|
|
|
|||
|
|
@ -216,17 +216,17 @@ def grpo_trainer__generate_and_score_completions(function_name, function):
|
|||
replacement_lines = """
|
||||
batch_size = self.args.per_device_train_batch_size if mode == "train" else self.args.per_device_eval_batch_size
|
||||
try:
|
||||
#TRL 0.23.1 and below path
|
||||
# TRL 0.23.1 and below path
|
||||
if not has_images:
|
||||
# Left pad prompt before calculation old and ref hidden states
|
||||
prompt_completion_ids = left_pack_padding(prompt_completion_ids, self.processing_class.pad_token_id)
|
||||
self.model.for_training()
|
||||
except:
|
||||
#TRL 0.24.0 and below path
|
||||
except:
|
||||
# TRL 0.24.0 and below path
|
||||
if images is None:
|
||||
# Left pad prompt before calculation old and ref hidden states
|
||||
prompt_completion_ids = left_pack_padding(prompt_completion_ids, self.processing_class.pad_token_id)
|
||||
self.model.for_training()"""
|
||||
self.model.for_training()"""
|
||||
|
||||
function = function.replace(line_to_replace, replacement_lines)
|
||||
|
||||
|
|
|
|||
|
|
@ -91,6 +91,7 @@ VLLM_SUPPORTED_VLM = [
|
|||
"qwen2_5_vl",
|
||||
"gemma3",
|
||||
"mistral3",
|
||||
"qwen3_vl",
|
||||
]
|
||||
VLLM_NON_LORA_VLM = [
|
||||
"mllama",
|
||||
|
|
|
|||
Loading…
Reference in a new issue