Commit graph

2,628 commits

Author SHA1 Message Date
Daniel Han
bef2b47599 Update llama.py 2025-07-20 03:19:10 -07:00
Daniel Han
48296987a3 Update llama.py 2025-07-20 03:17:02 -07:00
Daniel Han
9c6b199716 Update synthetic.py 2025-07-20 00:10:41 -07:00
Daniel Han
27503af0dc Update synthetic.py 2025-07-19 03:36:53 -07:00
Daniel Han
75f615891a Update synthetic.py 2025-07-19 03:18:18 -07:00
Daniel Han
6a65ee478c Update synthetic.py 2025-07-19 03:11:33 -07:00
Daniel Han
36ba3c7c69 Update synthetic.py 2025-07-19 02:54:28 -07:00
Daniel Han
bb0abf54df Merge branch 'main' into nightly 2025-07-19 01:29:41 -07:00
Quentin Gallouédec
580b5bca11 Update README.md (#2991)
* Update README.md

* Update README.md
2025-07-18 15:43:59 -07:00
Daniel Han
f32ee75b45 Merge branch 'main' into nightly 2025-07-18 05:37:10 -07:00
Daniel Han
67b16ae5c0 Bug fixes (#2998)
* 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

* 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 4021da634a.

* skip_guard_eval_unsafe fix
2025-07-18 05:36:15 -07:00
Daniel Han
83892cd097 skip_guard_eval_unsafe fix 2025-07-18 05:31:21 -07:00
Daniel Han
ce6a73986d Revert "Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model me…" (#2990)
This reverts commit 4021da634a.
2025-07-17 15:37:23 -07:00
Daniel Han
5ee84edade Merge branch 'main' into nightly 2025-07-17 15:36:24 -07:00
Daniel Han
4021da634a Revert "Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model merge erro…" (#2988)
This reverts commit 4565698ca5.
2025-07-17 15:35:28 -07:00
Roland Tannous
4565698ca5 Add Qwen2.5-VL-32B-Instruct mapping to fix quantized model merge error (#2986) 2025-07-17 15:35:05 -07:00
DoubleMathew
6cdc11816d use fastmodel (#2987) 2025-07-17 15:34:14 -07:00
Quentin Gallouédec
2960bf8d94 Update unsloth-cli.py (#2985) 2025-07-17 15:08:38 -07:00
Daniel Han
3824a6ad78 Bug fixes (#2982)
* 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

* 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
2025-07-17 07:02:38 -07:00
Daniel Han
06da87c79a Update rl_replacements.py 2025-07-17 06:54:25 -07:00
Daniel Han
9d8f2e4c83 Update rl_replacements.py 2025-07-17 06:51:59 -07:00
Daniel Han
8d983b01ff Update rl_replacements.py 2025-07-17 06:49:21 -07:00
Daniel Han
640032f115 Update rl_replacements.py 2025-07-17 06:47:23 -07:00
Daniel Han
2ae069ab2d Update rl_replacements.py 2025-07-17 06:44:28 -07:00
Daniel Han
5ad0f54c2d Update rl_replacements.py 2025-07-17 06:44:13 -07:00
Daniel Han
23dbf731a9 Update rl_replacements.py 2025-07-17 06:39:59 -07:00
Daniel Han
6c1a57ee4d Update rl.py 2025-07-17 06:30:26 -07:00
Daniel Han
f6b6ab7a1b Update rl_replacements.py 2025-07-17 06:26:10 -07:00
Daniel Han
0a67f44bb6 Update rl_replacements.py 2025-07-17 06:25:21 -07:00
Daniel Han
e66792eb05 Update rl_replacements.py 2025-07-17 06:24:33 -07:00
Daniel Han
771d5ff25f Update rl_replacements.py 2025-07-17 06:23:37 -07:00
Daniel Han
72e2debbd6 Update pyproject.toml 2025-07-17 05:38:04 -07:00
Daniel Han
f3606ea3d9 Update pyproject.toml 2025-07-17 05:26:58 -07:00
Daniel Han
1185706555 Merge branch 'main' into nightly 2025-07-17 05:14:52 -07:00
Daniel Han
2c468550e6 Revert "GRPO Fix - Support vllm pre-dequantized quantization states in fast_dequantize kernel (#2943)"
This reverts commit 1cefffa2d2.
2025-07-17 05:02:08 -07:00
Daniel Han
03c880f5da Update _utils.py 2025-07-17 02:08:49 -07:00
Daniel Han
c88758124a compiler stance 2025-07-17 01:40:49 -07:00
Daniel Han
aa8e172396 Update vision.py 2025-07-17 01:19:07 -07:00
Daniel Han
b112838f58 Update vision.py 2025-07-17 00:33:27 -07:00
Daniel Han
98cebf3d06 Update _utils.py 2025-07-14 02:45:19 -07:00
Daniel Han
e718c27474 Merge branch 'main' into nightly 2025-07-14 02:44:42 -07:00
Roland Tannous
1cefffa2d2 GRPO Fix - Support vllm pre-dequantized quantization states in fast_dequantize kernel (#2943)
* Support pre-dequantized quantization states in fast_dequantize kernel

* has_nested_quant conditional set to  only

* Update utils.py

* Update utils.py

---------

Co-authored-by: Daniel Han <danielhanchen@gmail.com>
2025-07-14 02:41:15 -07:00
Roland Tannous
32738da0d1 fix dataloader_num_workers value error in GRPOTrainer (#2944) 2025-07-14 01:43:33 -07:00
Muzammil Khan
1eaa52ae55 fix: change lora_dropout from int to float for type consistency (#2949)
Fixes "Argument of type 'float' cannot be assigned to parameter 'lora_dropout' of type 'int'" error by ensuring lora_dropout is consistently a float (0.0) rather than int (0) across vision.py, llama.py, and unsloth-cli.py
2025-07-14 01:42:07 -07:00
Datta Nimmaturi
665a8e4b1d Fix falcon H1 dropout issue (#2938)
Because we don't have down and gate multipliers, the MLP output values are too huge, causing NaN and unstable training. To bypass that lets rely on HF's implementation for the time being
2025-07-12 15:53:07 -07:00
DoubleMathew
bbcba7fc21 patch falcon h1 inference (#2932) 2025-07-12 15:52:24 -07:00
Daniel Han
01f649f6fc Update rl.py 2025-07-11 03:13:55 -07:00
Daniel Han
7c8cd3dd6d Update rl.py 2025-07-11 03:11:07 -07:00
Daniel Han
7d2106e5c6 Merge branch 'main' into nightly 2025-07-11 03:04:28 -07:00
Daniel Han
f155097cd8 Uninitialized handler 2025-07-11 03:04:17 -07:00