Commit graph

202 commits

Author SHA1 Message Date
Manan17
e8f9610122 Changing labels in dataset card 2026-02-15 06:34:39 +00:00
Manan17
45618fb43c Adding hint for password length 2026-02-15 06:12:55 +00:00
Manan17
ace86ed0b8 Fixing stuck training processes 2026-02-15 05:40:06 +00:00
Roland Tannous
2c5a4359c6 Merge pull request #81 from unslothai/feature/early-stop-or-cancel-training-ui
feat: early stop or cancel training UI
2026-02-15 08:28:39 +04:00
Manan17
52cbf9b699 feat: UI for cancel or save and stop training 2026-02-15 00:22:28 +00:00
Manan17
97c6a09b84 feat: add cancel or save and stop training 2026-02-15 00:00:22 +00:00
Roland Tannous
1d362a36c3 Merge pull request #79 from unslothai/feat/compare-use-adapter
Adapter Toggling for chat compare feature
2026-02-15 00:25:53 +04:00
Roland Tannous
b334e49498 decouple reliance of backend on frontend for is_lora 2026-02-14 20:13:50 +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
Wasim Yousef Said
6ed179b459 Merge pull request #78 from unslothai/feature/vision-capabilities-chat
feat(chat): add vision image attachments for OpenAI-compatible chat
2026-02-14 02:01:17 -08:00
Shine1i
7611c7122c feat: add image handling support with Vision adapter and base64 serialization in chat runtime 2026-02-14 10:59:10 +01:00
Roland Tannous
c843a93797 Merge pull request #76 from unslothai/feature/inference-vision-openai-compatible
PR: OpenAI-compatible multimodal vision support + true vision streaming
2026-02-14 13:47:39 +04:00
Roland Tannous
418a374125 migrate _generate_vision_response to use TextIteratorStreamer + background thread 2026-02-14 09:30:32 +00:00
Roland Tannous
9de38cb773 feat(inference): accept OpenAI multimodal content parts (image_url) in /chat/completions 2026-02-14 09:06:25 +00:00
Roland Tannous
44d52b4103 Merge pull request #72 from unslothai/fix/sse-progress-timeout
Fix: SSE progress stream timeout during training
2026-02-14 09:58:14 +04:00
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
957e39c50d Merge pull request #71 from unslothai/fix/frontend-default-path
Fix/frontend default path
2026-02-14 09:43:24 +04:00
Roland Tannous
414d173624 replace function with alias 2026-02-14 05:28:47 +00:00
Roland Tannous
e09c5dfc7e fix alias command 2026-02-14 05:24:54 +00:00
Roland Tannous
7260c09268 change line arguments order in setup.sh 2026-02-14 05:13:49 +00:00
Roland Tannous
6b2a777f97 fix path in run_server 2026-02-14 05:06:17 +00:00
Roland Tannous
f07b919385 change default frontend path in run.py to studio/frontend/dist 2026-02-14 05:02:26 +00:00
Roland Tannous
933048d4f7 Merge pull request #70 from unslothai/feat/wire-custom-format-mapping-to-training
feat: wire `custom_format_mapping` through training pipeline
2026-02-14 01:09:35 +04:00
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
f12c5f61ef Merge pull request #69 from unslothai/fix/auto-detect-lora-in-model-config
fix: auto-detect LoRA adapters for both local and remote HF models in ModelConfig
2026-02-14 00:56:34 +04:00
Roland Tannous
8ce96df66f fix: auto-detect LoRA adapters for both local and remote HF models in ModelConfig 2026-02-13 20:54:40 +00:00
Roland Tannous
3d33753899 Merge pull request #68 from unslothai/fix/datasets-fix-vlm-detection
fix: auto-detect multimodal datasets in /check-format without requiri…
2026-02-14 00:04:51 +04:00
Wasim Yousef Said
bdcaf5518c Merge pull request #66 from unslothai/ui-fixes
UI fixes
2026-02-13 11:29:32 -08:00
Wasim Yousef Said
1f50b5b5f1 Merge pull request #67 from unslothai/style/polish-chat-sidebar-spacing
style: polish chat page spacing, typography adjustment, and panel alignment
2026-02-13 11:28:56 -08:00
Manan17
2210545493 fixing padding for titles 2026-02-13 19:22:39 +00:00
imagineer99
59acc087b6 style: polish chat page spacing, small typography, and panel alignment 2026-02-13 19:18:20 +00:00
Manan17
c0fbe7d4a5 Change of font space for title 2026-02-13 19:03:51 +00:00
Roland Tannous
a62a30bd9b Merge pull request #65 from unslothai/refactor/change-highlighted-text-color
Refactor/change highlighted text color
2026-02-13 21:36:08 +04:00
Roland Tannous
adf1ef5ea5 fix: auto-detect multimodal datasets in /check-format without requiring is_vlm flag 2026-02-13 17:29:39 +00:00
Manan17
acc00bd0a4 Changing the highlighted text color to be black while keeping the checkmark emerald 2026-02-13 17:24:57 +00:00
Wasim Yousef Said
6935fc3593 Merge pull request #63 from unslothai/feature/chat-openai-integration
feat(chat): integrate backend chat runtime + model load flow
2026-02-13 08:47:44 -08:00
Shine1i
ce7c9917ab feat: refactor suggestion handling and centralize defaults for thread UI 2026-02-13 17:42:45 +01:00
Shine1i
5fe4258401 feat: add warm-up indicator, new thread feature, and runtime improvements in chat UI 2026-02-13 17:28:01 +01:00
Roland Tannous
fe5a46ede3 Merge pull request #62 from unslothai/feature/add-easydict-addict
Feature/add easydict addict
2026-02-13 20:22:46 +04:00
Roland Tannous
965be3f5dc add easydict and addict to setup file 2026-02-13 16:19:55 +00:00
Shine1i
c9c4463d5d feat: integrate LoRA model management with UI and runtime synchronization 2026-02-13 17:14:49 +01:00
Shine1i
23d2cfd09d feat: refactor chat runtime with modular APIs, state management, and runtime synchronization 2026-02-13 16:45:00 +01:00