ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
386 commits 391 branches 58 tags 304 MiB
Commit graph

51 commits

Author SHA1 Message Date
Roland Tannous
adc0c78dbc reduce dataset_num_proc to 1/4 of cpu_count 2026-02-18 20:53:32 +00:00
Roland Tannous
e33920974b fix: unwrap ProcessorMixin to raw tokenizer for text-only SFTTrainer on VLM-architecture models 2026-02-18 19:13:20 +00:00
Roland Tannous
a6e2fa5b3a Merge remote-tracking branch 'origin/nightly' into fix/dataset-mapping-vlm-text-datasets 2026-02-18 18:11:45 +04:00
Manan17
76cd1dc24c fixing the hangup of training after multiple back to back training processes 2026-02-18 08:18:13 +00:00
Manan17
c37bf686a6 Dividing the total cpu_count // 3 2026-02-18 07:59:57 +00:00
Manan17
58116e7e7a fix the linear path on backend 2026-02-18 07:08:32 +00:00
Roland Tannous
d7853efd21 debug statements 2026-02-18 00:37:09 +00:00
Roland Tannous
0d8b67b706 fix: normalize target_modules [all-linear] list to string for Unsloth/PEFT compatibility 2026-02-18 00:32:21 +00:00
Roland Tannous
d2332622d1 fix: defensively rename VLM chat column to match model's forward() signature 2026-02-17 23:49:13 +00:00
Shine1i
dc0cec772d feat: enhance training stop and reset flow with detailed checks 2026-02-17 23:32:22 +01:00
Roland Tannous
c9fdce63e7 fix: skip sudo check on WSL during GGUF export to prevent password prompt hang 2026-02-17 19:30:02 +00:00
Shine1i
0be3e6f525 feat: integrate gradient norm tracking in training runtime and metrics 
- Enhanced chart logic to filter and visualize finite gradient norm values.
 2026-02-17 18:26:59 +01:00
Manan17
c7b7ecab4f Adding metadata for checkpoints 2026-02-16 23:46:17 +00:00
Wasim Yousef Said
7b8220598e Merge pull request #124 from unslothai/feature/bug-fixes 
feat: support disabling top-k sampling with -1 and standardize normalization
 2026-02-16 13:21:12 -08:00
Roland Tannous
ff0aec180a Merge branch 'nightly' into feature/eval-split-auto-detection 2026-02-17 01:11:30 +04:00
Shine1i
0db7da96cc feat: support disabling top-k sampling with -1 and standardize normalization logic 
- Updated top-k parameter range to accept -1 in models and frontend.
- Added utility to normalize top-k for backend compatibility.
 2026-02-16 21:33:24 +01:00
Roland Tannous
fa0ca59215 feat: auto-detect model+dataset compatibility to select VLM vs LLM training path 2026-02-16 19:18:49 +00:00
Roland Tannous
5df3a0b250 feat: add eval_enabled flag and format-first-then-split for eval dataset 2026-02-16 14:13:55 +00:00
Roland Tannous
0aea3f149d feat: add eval split auto-detection, eval_steps hyperparam, and eval_loss chart integration 2026-02-16 13:51:10 +00:00
Roland Tannous
37452d56cf feat: add eval split auto-detection, eval_steps hyperparam, and eval_loss chart integration 2026-02-16 13:38:54 +00:00
Roland Tannous
f0298edeb8 refactor: move checkpoint scanning to utils/models and /checkpoints endpoint to models router 2026-02-16 09:32:11 +00:00
Roland Tannous
6ecc03485d Merge pull request #97 from unslothai/fix/progress-metics 
Resolved the progress metrics
 2026-02-16 11:55:01 +04:00
sshah229
63b34660ed modified the num_tokens logic 2026-02-16 00:38:40 -07:00
Roland Tannous
909955767b feat: add min_p sampling parameter to /chat/completions generation pipeline 2026-02-16 06:33:17 +00:00
Manan17
19276ae60b Fixing the get checkpoint api 2026-02-16 04:47:28 +00:00
Roland Tannous
d0964652af feat: thread dataset subset/split params from API routes through to load_dataset calls 2026-02-16 03:56:22 +00:00
Shine1i
571959e383 feat: add cancelation support for chat generation and streaming tasks 2026-02-15 18:23:27 +01:00
sshah229
0b1c635b43 resolved the prgress metrics 2026-02-15 05:35:32 -07:00
Manan17
6e4cde3bf8 Adding save-steps to the SFTConfig 2026-02-15 09:37:54 +00:00
Manan17
6ccbc4edce Fixing stuck training processes 2026-02-15 05:38:06 +00:00
Manan17
97c6a09b84 feat: add cancel or save and stop training 2026-02-15 00:00:22 +00:00
Roland Tannous
be3934860f strip extra debug statements 2026-02-14 19:23:51 +00:00
Roland Tannous
3ff3def555 replace model unloading and peft loading mechanism for compare feature 2026-02-14 19:18:49 +00:00
Roland Tannous
e7ae901737 del model.peft_config instead of using model.delete_adapter 2026-02-14 17:32:15 +00:00
Roland Tannous
7d8e991c1f added print statements for activate_lora_adapter 2026-02-14 17:25:37 +00:00
Roland Tannous
6fefbe9f0b swipped logger for print statements as logger isn't propagating 2026-02-14 17:21:26 +00:00
Roland Tannous
d0b94eae75 added logging 2026-02-14 17:09:07 +00:00
Roland Tannous
b5c8136957 exclude default from model.delete_adapter 2026-02-14 17:03:52 +00:00
Roland Tannous
35a6e40268 _apply_adapter_state now calls revert_to_base_model and activate_lora_adapter properly 2026-02-14 16:57:24 +00:00
Roland Tannous
f67ee58347 feat(inference): add use_adapter field for per-request adapter toggling in compare mode 2026-02-14 14:52:13 +00:00
Roland Tannous
418a374125 migrate _generate_vision_response to use TextIteratorStreamer + background thread 2026-02-14 09:30:32 +00:00
Roland Tannous
4f0fad2156 fix: increase SSE progress timeout to 30min and allow step-0 updates 2026-02-14 05:47:22 +00:00
Roland Tannous
67edebfeb3 feat: wire custom_format_mapping through training pipeline to format_and_template_dataset 2026-02-13 21:07:36 +00:00
Roland Tannous
f52bddc23f refactor: remove gradio dependency from training backend 2026-02-13 09:25:49 +00:00
Roland Tannous
75f775d088 fix: change epoch type from int to float to match TrainerState 2026-02-13 06:51:55 +00:00
Roland Tannous
da1cde971c use get_device() for device selection and clear_gpu_cache() for GPU memory cleanup in inference, trainer, and export 2026-02-11 16:56:52 +00:00
Roland Tannous
59d5f24eb5 integrate global hardware detection at lifespan entrypoint 2026-02-11 15:34:26 +00:00
Roland Tannous
107bd2be4c feat: add Apple Silicon (MPS) compatibility to backend utils + tests 2026-02-11 14:00:39 +00:00
Roland Tannous
b4ec0389f0 refactor/inference-api-routes-part-1 2026-02-03 16:57:57 +00:00
Roland Tannous
62ddcfa019 Refactor [dataset_utils.py](cci:7://file:///home/support/new-ui-prototype/studio/backend/utils/datasets/dataset_utils.py:0:0-0:0) into focused modules 2026-02-03 14:38:02 +00:00