Daniel Han
|
7854bc2cb8
|
Merge branch 'main' into nightly
|
2025-02-06 03:49:16 -08:00 |
|
Daniel Han
|
c8e4d4b767
|
Update
|
2025-02-06 03:23:54 -08:00 |
|
Daniel Han
|
5d6275c957
|
Update _utils.py
|
2025-02-06 02:44:46 -08:00 |
|
Daniel Han
|
e288d96272
|
Update pyproject.toml
|
2025-02-06 02:44:23 -08:00 |
|
Daniel Han
|
144190bd06
|
GRPO, vLLM, Bug Fixes, Reinforcement Learning (#1620)
* use exact model name
* Update save.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* print
* Update _utils.py
* Update _utils.py
* Update llama.py
* Update _utils.py
* Update vision.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update loader.py
* accurate_accumulation
* Update loader.py
* Update loader.py
* Update _utils.py
* Update loader.py
* Update loader.py
* Update loader.py
* Update loader.py
* Update pyproject.toml
* Update __init__.py
* Update pyproject.toml
* Update __init__.py
* Update __init__.py
* Fix Triton heuristics
https://github.com/triton-lang/triton/issues/5224
* Update __init__.py
* Update __init__.py
* Update __init__.py
* Update __init__.py
* Xformers
* Update loader.py
* Update loader.py
* Rewind
* Update _utils.py
* Update _utils.py
* requires grad
* Update loader.py
* Update _utils.py
* Update loader.py
* changing model to base_model if peft model is already used
* Improve debugging experience (#1512)
* Create CONTRIBUTING.md (#1472)
Creating contributing guidelines
* Update CONTRIBUTING.md
improved sentence
* Improve logging control in `unsloth_compile_transformers` by conditionally redirecting stdout based on UNSLOTH_DISABLE_LOGGER environment variable
---------
Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com>
Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com>
* Update loader.py
* Update llama.py
* Update llama.py
* Revert "Update llama.py"
This reverts commit a8edd0931a.
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Auto change is_bfloat16_supported
* Update llama.py
* Force data-type
* Update llama.py
* All attention refactor fix (#1491)
* change initilization of n_heads, n_kv_heads, hidden_size in llama.py
* do the same for cohere, mistral, gemma2, granite
* do the same for flexattention,cohere, mistral, granite
* Update llama.py
* Update llama.py
* Update granite to work with latest post_patch methods (#1502)
* Update granite to work with latest post_patch methods
* Pass position_embeddings for granite even if transformers<4.47
* Update llama.py
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Minor fixes for granite models (#1503)
* Update granite.py
Grab residual multiplier directly from layer
* Update llama.py
Version should read >= 4.47.1 as that is the version requiring the changes
* Update granite.py
* Update llama.py
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* support modelscope models and datasets (#1481)
* support modelscope
* change modelscope args
* remove useless import
* remove useless import
* fix
* wip
* fix
* remove useless code
* add readme
* add some comments
* change print to raise error
* update comment
* Update loader.py
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Merge branch 'main' into nightly
* Phi 4
* Update llama.py
* Torch.Cuda Is Available Condition and Warning (#1545)
* check for torch.cuda and triton if available
on my machine(mac m3) the cuda were not available
* Update pyproject.toml
* Update __init__.py
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Update mistral.py
* Update mistral.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Update _utils.py
* Fix
* Bug fixes
* Update mapper.py
* Add dropout to granite to match HF's implementation (#1557)
Signed-off-by: datta0 <venkatadattasainimmaturi@gmail.com>
* Update llama.py
* Update llama.py
* Bug fixes
* fix: flash_attn_detection_error (#1556)
* fix: flash_attn_detection_error
* Update _utils.py
---------
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
* Update mapper.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* Update gemma.py
* dim fix
* Update _utils.py
* Torch 2.6 support
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Faster inference?
* Update llama.py
* Update llama.py
* Update utils.py
* Update llama.py
* Update llama.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update mapper.py
* Fast Inference via vLLM
* Update llama.py
* Update llama.py
* Update utils.py
* Create rl.py
* PatchRL
* Update rl.py
* Update rl.py
* Update rl.py
* PatchRLStatistics
* Update rl.py
* Update rl.py
* Update rl.py
* Update utils.py
* Update utils.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* RL metrics
* Update rl.py
* RL metrics
* Update __init__.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update chat_templates.py
* Update mapper.py
* Fp8 cache
* Update llama.py
* Update llama.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update rl.py
* Update __init__.py
* Update loader.py
---------
Signed-off-by: datta0 <venkatadattasainimmaturi@gmail.com>
Co-authored-by: Itsuro Tajima <tajima@georepublic.de>
Co-authored-by: Muhammad Osama <muhammadosama1994@gmail.com>
Co-authored-by: Edd <68678137+Erland366@users.noreply.github.com>
Co-authored-by: Michael Han <107991372+shimmyshimmer@users.noreply.github.com>
Co-authored-by: Nino Risteski <95188570+NinoRisteski@users.noreply.github.com>
Co-authored-by: Kareem <81531392+KareemMusleh@users.noreply.github.com>
Co-authored-by: Datta Nimmaturi <datta.nimmaturi@nutanix.com>
Co-authored-by: Z <coffeevampirebusiness@gmail.com>
Co-authored-by: tastelikefeet <58414341+tastelikefeet@users.noreply.github.com>
Co-authored-by: AminWhat <88392440+aminwhat@users.noreply.github.com>
Co-authored-by: Zhe Zhang <2631992879@qq.com>
|
2025-02-06 02:41:12 -08:00 |
|
Daniel Han
|
9dd1219358
|
Update loader.py
|
2025-02-06 02:36:42 -08:00 |
|
Daniel Han
|
7d9a7aaa3d
|
Update __init__.py
|
2025-02-06 02:32:34 -08:00 |
|
Daniel Han
|
79d2b0aea3
|
Update rl.py
|
2025-02-06 02:31:01 -08:00 |
|
Daniel Han
|
d6ff188cec
|
Update rl.py
|
2025-02-06 02:24:13 -08:00 |
|
Daniel Han
|
965dee5f5e
|
Update rl.py
|
2025-02-06 02:21:08 -08:00 |
|
Daniel Han
|
e71a8aa101
|
Update rl.py
|
2025-02-06 02:14:59 -08:00 |
|
Daniel Han
|
68da8b69b7
|
Update rl.py
|
2025-02-06 01:57:37 -08:00 |
|
Daniel Han
|
da966a4e1c
|
Update rl.py
|
2025-02-06 01:50:22 -08:00 |
|
Daniel Han
|
fc4555c288
|
Update rl.py
|
2025-02-06 01:47:44 -08:00 |
|
Daniel Han
|
e20efe32a3
|
Update rl.py
|
2025-02-06 01:16:43 -08:00 |
|
Daniel Han
|
10d65ea437
|
Update rl.py
|
2025-02-06 01:12:33 -08:00 |
|
Daniel Han
|
4724be861e
|
Update rl.py
|
2025-02-06 01:10:42 -08:00 |
|
Daniel Han
|
eb1f9b91f1
|
Update rl.py
|
2025-02-06 01:08:31 -08:00 |
|
Daniel Han
|
5c0ed78b9b
|
Update rl.py
|
2025-02-06 01:07:00 -08:00 |
|
Daniel Han
|
c998665f0b
|
Update rl.py
|
2025-02-06 01:06:40 -08:00 |
|
Daniel Han
|
c7f2ec3338
|
Update rl.py
|
2025-02-06 01:06:20 -08:00 |
|
Daniel Han
|
d52341f06b
|
Update rl.py
|
2025-02-06 01:05:48 -08:00 |
|
Daniel Han
|
71c34db351
|
Update rl.py
|
2025-02-06 01:02:31 -08:00 |
|
Daniel Han
|
32f09a14d6
|
Update rl.py
|
2025-02-06 00:59:13 -08:00 |
|
Daniel Han
|
b196ba85ca
|
Update llama.py
|
2025-02-05 20:30:36 -08:00 |
|
Daniel Han
|
6719a6134b
|
Update llama.py
|
2025-02-05 20:24:33 -08:00 |
|
Daniel Han
|
18de8f29c8
|
Fp8 cache
|
2025-02-05 20:00:02 -08:00 |
|
Daniel Han
|
b8a833e1af
|
Update mapper.py
|
2025-02-05 18:31:01 -08:00 |
|
Daniel Han
|
7cc03b2b51
|
Update chat_templates.py
|
2025-02-05 17:52:36 -08:00 |
|
Daniel Han
|
9455082740
|
Update rl.py
|
2025-02-05 15:36:59 -08:00 |
|
Daniel Han
|
1ff75a7dc7
|
Update rl.py
|
2025-02-05 15:21:53 -08:00 |
|
Daniel Han
|
c0805c415f
|
Update rl.py
|
2025-02-05 15:16:44 -08:00 |
|
Daniel Han
|
ba0a2871c2
|
Update __init__.py
|
2025-02-05 15:11:40 -08:00 |
|
Daniel Han
|
093cd0cde3
|
RL metrics
|
2025-02-05 15:08:10 -08:00 |
|
Daniel Han
|
cc6bb7d1db
|
Update rl.py
|
2025-02-05 15:02:52 -08:00 |
|
Daniel Han
|
8ce4a73bfc
|
RL metrics
|
2025-02-05 14:59:01 -08:00 |
|
Daniel Han
|
b7bd548779
|
Update rl.py
|
2025-02-05 07:28:16 -08:00 |
|
Daniel Han
|
9b76d49761
|
Update rl.py
|
2025-02-05 07:27:07 -08:00 |
|
Daniel Han
|
cc927d2d18
|
Update rl.py
|
2025-02-05 07:25:05 -08:00 |
|
Daniel Han
|
d7c3f9cba6
|
Update rl.py
|
2025-02-05 07:13:40 -08:00 |
|
Daniel Han
|
aebeeb4901
|
Update rl.py
|
2025-02-05 06:58:04 -08:00 |
|
Daniel Han
|
8506d6be95
|
Update rl.py
|
2025-02-05 06:56:12 -08:00 |
|
Daniel Han
|
e59e196448
|
Update rl.py
|
2025-02-05 06:50:39 -08:00 |
|
Daniel Han
|
7e7fc35625
|
Update rl.py
|
2025-02-05 06:50:14 -08:00 |
|
Daniel Han
|
6aa0fc7e28
|
Update rl.py
|
2025-02-05 06:48:54 -08:00 |
|
Daniel Han
|
a6f919f60c
|
Update rl.py
|
2025-02-05 06:44:18 -08:00 |
|
Daniel Han
|
eed2ac7329
|
Update rl.py
|
2025-02-05 06:41:37 -08:00 |
|
Daniel Han
|
bfe87a51bf
|
Update rl.py
|
2025-02-05 06:37:32 -08:00 |
|
Daniel Han
|
0aa4c035e8
|
Update rl.py
|
2025-02-05 06:32:51 -08:00 |
|
Daniel Han
|
ea55289b5a
|
Update rl.py
|
2025-02-05 06:28:54 -08:00 |
|