* 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 commit |
||
|---|---|---|
| .. | ||
| README.md | ||
| test_hf_qlora_train_and_merge.py | ||
| test_unsloth_qlora_train_and_merge.py | ||
QLoRA Train and Merge Tests
Overview
Tests that performing QLoRA training and merging weights to 16-bits post-training maintains same behavior as trained model.
test_unsloth_qlora_train_and_merge.py: Test Unsloth QLoRA train and merge usingFastLanguageModel.from_pretrained,FastLanguageModel.get_peft_model, andFastLanguageModel.save_pretrained_mergedapistest_hf_qlora_train_and_merge.py: Test Hugging Face QLoRA train and merge usingfrom_pretrained,get_peft_model, andmerge_and_unloadapis.- Demonstrates that
peft'smerge_and_unloadresults in loss of accuracy as it requantizes the base layer after merging adapter weights so that the model still containsLinear4Bitlayers post merging. - I (@jeromeku) implemented a custom merge function that replaces all
LoraLayerswithLinearlayers whose weights are the dequantized base layer weights with adapter weights merged (compute done in fp32, cast to original dtype after merging), roughly equivalent toFastLanguageModel.save_pretrained_merged.
- Demonstrates that
Usage
Run unsloth test:
python tests/qlora/test_unsloth_qlora_train_and_merge.py
Run huggingface test:
python tests/qlora/test_hf_qlora_train_and_merge.py
Details
The tests train a QLoRA model on a single prompt dataset
QUESTION = "What day was I born?"
ANSWER = "January 1, 2058"
USER_MESSAGE = {"role": "user", "content": QUESTION}
ASSISTANT_MESSAGE = {"role": "assistant", "content": ANSWER}
Given that the answer is impossible to answer accurately without finetuning, we can only expect the model to answer the question correctly if the model has been trained on the question.
To check this behavior, we check the model's response to the question before and after training and after merging, checking that the model's response contains the answer after training and merging but not before training.
Results
For the unsloth test, the model's behavior is as expected:
- before training, the model's response does not contain the answer
- after training, the model's response contains the answer
- after merging, the model's response contains the answer
For the huggingface test, the model's behavior is as expected:
- before training, the model's response does not contain the answer
- after training, the model's response contains the answer
- after using peft's
merge_and_unload, the model's response does not contain the answer - after using my custom merge function, the model's response contains the answer
The scripts should output training params, training logs, as well as model responses before and after training and after merging (only prints model responses if answer is not contained in response).