Shine1i
ba000dc0f2
feat: add "Multi-Turn Chat" learning recipe with structured conversation outputs
...
- Introduced "Multi-Turn Chat" recipe to generate structured user-assistant conversations with domain/topic-based goals and constraints.
- Added `conversation.json` with model configuration, sampling strategies, and LLM prompts.
- Updated UI nodes, layout, and graph rendering logic to support new recipe.
- Enhanced `recipe-studio` fit view logic to improve editor layout responsiveness.
2026-02-24 02:38:36 +01:00
Shine1i
dec6b4b224
feat: add new learning recipes for diverse data transformations
...
- Added three new learning recipes: "Instruction from Answer," "PDF Grounded QA," and "Structured Outputs Jinja," with respective metadata and configuration.
- Integrated support for unstructured and structured input handling, including sampling strategies, prompt definitions, and model specifications.
- Enhanced JSON structure and UI nodes to facilitate better recipe visualization and execution.
2026-02-24 01:50:55 +01:00
Shine1i
5254f04065
feat: add layout direction support and enhance handle logic
...
- Introduced `layoutDirection` to control graph orientation ("LR" or "TB") and integrate into edges, nodes, and payloads.
- Enhanced handle management with new default, semantic, and data-specific mappings based on layout direction.
- Added handle normalization for consistent connections across layouts and semantic/data flows.
- Updated UI to reflect layout-aware positioning and semantic connections.
2026-02-24 00:51:49 +01:00
Shine1i
9f574941f9
feat: normalize handle IDs and enhance scorer options UI
...
- Added handle normalization functions to standardize handle IDs across connections.
- Expanded UI for scorer options with real-time updates, input fields for values and descriptions, and support for adding/removing options.
- Updated graph node handles and their layout logic for better connection visualization.
- Stripped sensitive fields (e.g., `api_key`) from payloads during export.
2026-02-24 00:29:14 +01:00
Shine1i
ad95b4a951
feat: add "Instruction from Answer" learning recipe and badge display enhancements
...
- Introduced a new "Instruction from Answer" learning recipe with related metadata, payload integration, and UI updates.
- Enhanced badge display logic to include up to 3 badges with overflow indication for additional learning badges.
2026-02-24 00:25:21 +01:00
Shine1i
ab31aa9ed4
feat: add per-column seed drop support with UI integration, validation, and payload enhancements
2026-02-23 23:33:59 +01:00
Shine1i
54382c659c
feat: add support for learning recipes with template loading, dialog integration, and enhanced payload handling
2026-02-23 23:20:32 +01:00
Shine1i
71916f1dce
feat: add ShineBorder UI component and learning recipe templates to enhance data recipes page
2026-02-23 22:38:06 +01:00
Shine1i
8739a01f56
Merge branch 'nightly' into feature/canvas-lab
2026-02-23 21:54:35 +01:00
Shine1i
b8231a6be6
refactor: keep seed block pos
2026-02-23 21:53:32 +01:00
Shine1i
1323e0af53
refactor: add batch processing support with configuration options and execution enhancements
2026-02-23 21:32:20 +01:00
Shine1i
59a15cb5bc
refactor: enhance recipe validation flows with error collection, seed-specific updates, and improved UX in execution dialogs
2026-02-23 20:34:53 +01:00
Shine1i
d4655eb8bf
refactor: streamline recipe execution flows with validation support and enhanced run dialog interactions
2026-02-23 20:28:41 +01:00
Shine1i
91cbb0e933
refactor: improve dialog rendering and logging setup for stability and configurability
2026-02-23 20:16:03 +01:00
Shine1i
71ab9ff4b4
refactor: enhance seed configuration handling with added fields, dynamic chunking logic, and streamlined interactions
2026-02-23 19:40:13 +01:00
Shine1i
424b00b701
refactor: improve seed source handling with additional type support, enhanced parsing logic, and text chunking optimization
2026-02-23 19:29:54 +01:00
Shine1i
3e17e2b0f6
refactor: enhance seed source handling with new source types and streamlined inspection flows
2026-02-23 18:46:02 +01:00
Roland Tannous
77b0978d5f
Merge pull request #228 from unslothai/fix/cap-num-proc-multigpu-deadlock
...
Cap dataset.map num_proc on multi-GPU machines to prevent fork deadlocks
2026-02-23 19:04:22 +04:00
Roland Tannous
d74174f7f5
Cap dataset.map num_proc on multi-GPU machines to prevent fork deadlocks
2026-02-23 14:25:31 +00:00
Roland Tannous
4cb0cfdaf5
Remove firebase-debug.log and setup_leo.sh from tracking and add to .gitignore
2026-02-23 17:38:22 +04:00
Roland Tannous
2e2aa54ad2
Merge pull request #225 from unslothai/fix/fix-response-on-completion-truncation
...
fix: error on >30% sample drop after `train_on_responses_only` instead of silent DataLoader crash
2026-02-23 16:28:32 +04:00
Roland Tannous
3015916d26
fix: error on >30% sample drop after train_on_responses_only instead of silent DataLoader crash
2026-02-23 12:21:06 +00:00
Roland Tannous
b03938f6ad
Merge nightly into main Brings main up to date with nightly, including chat attachments, model-per-thread persistence, speech recognition, VRAM recommendations, MoE model configs, VLM fixes, and compile cache cleanup. Conflicts resolved by taking nightly's version for all diverged files (main-only changes were a feature add + immediate revert with net zero effect).
2026-02-23 14:52:57 +04:00
Roland Tannous
bfb84221fe
Merge pull request #221 from unslothai/feature/clear-unsloth-compile-cache
...
feat: clear unsloth_compiled_cache on startup, shutdown, and between …
2026-02-23 11:30:46 +04:00
Roland Tannous
dbbcdb4f09
feat: clear unsloth_compiled_cache on startup, shutdown, and between model loads
2026-02-23 07:26:22 +00:00
Roland Tannous
2a117f57a9
Merge pull request #220 from unslothai/feature/moe-training-models-configs
...
Add model defaults for MoE models (Qwen3 MoE, GLM Flash) and GLM response mapping
2026-02-23 10:09:27 +04:00
Roland Tannous
fb1c321ad3
Add GLM, Qwen3 MoE, TinyQwen3 MoE, and Ministral 3 VL model defaults and GLM train_on_responses_only mapping
2026-02-23 05:51:43 +00:00
Roland Tannous
bb1bd49a68
Merge pull request #217 from unslothai/fix/update-config-yamls
...
Fix vision LoRA defaults for VLMs and clean up text-only model configs
2026-02-22 19:14:54 +04:00
Roland Tannous
132cdb0547
fix: correct vision LoRA defaults for VLMs and remove vision fields from text-only model configs
2026-02-22 15:09:10 +00:00
Roland Tannous
7ac391d1e0
Merge pull request #215 from unslothai/fix/vlm-processing-class
...
fix: pass full Processor as processing_class for VLM SFTTrainer
2026-02-22 18:14:14 +04:00
Roland Tannous
202b7cdfa7
fix: pass full Processor as processing_class for VLM SFTTrainer
2026-02-22 14:11:12 +00:00
Roland Tannous
a4346b954e
Merge pull request #213 from unslothai/fix/fix-clear-chat-new-model
...
Fix: Clear Chat and Manage Model Lifecycle on Model Switch
2026-02-22 17:54:27 +04:00
Roland Tannous
761953b50e
feat(chat): persist model per thread and auto-load on thread switch
2026-02-22 13:35:45 +00:00
Roland Tannous
536a735acc
feat(chat): eject current model and start fresh thread on model switch
2026-02-22 13:17:03 +00:00
Roland Tannous
a490dca8a0
Merge pull request #211 from unslothai/fix/param-count-display
...
Fix: Remove download count fallback when model param count is unavailable
2026-02-22 16:52:25 +04:00
Roland Tannous
d3fbaa2256
Merge pull request #204 from unslothai/fix/image-preview-thumbnail
...
Fix: Resolve image preview thumbnail not rendering before send
2026-02-22 16:09:24 +04:00
Roland Tannous
36f10ea90e
Merge pull request #212 from unslothai/fix/stop-unclickable
...
Updated stop button to be unavailable during cancel training
2026-02-22 16:08:47 +04:00
Roland Tannous
c5a88ef90b
Merge pull request #208 from unslothai/revert-207-feature/attachment-restore
...
Revert "fix(chat): persist + hydrate user attachments in IndexedDB history"
2026-02-22 12:22:25 +04:00
Roland Tannous
df8e4bdc40
Merge pull request #203 from unslothai/feat/sort-unsloth-models-first
...
Feat: Sort unsloth models first in HF search dropdowns
2026-02-22 12:21:42 +04:00
Roland Tannous
75f3e5e2a1
feat: dual-query HF model search to surface all unsloth size variants first
2026-02-22 08:20:25 +00:00
imagineer99
4fe3772aa2
fix: remove download count fallback when model param count is unavailable
2026-02-22 06:30:50 +00:00
Wasim Yousef Said
4779ae8e61
Merge pull request #209 from unslothai/feature/attachment-restore
...
fix(chat): persist + hydrate user attachments in IndexedDB history
2026-02-21 22:17:18 -08:00
Roland Tannous
ac83e8b668
Revert "fix(chat): persist + hydrate user attachments in IndexedDB history"
2026-02-22 10:15:24 +04:00
Wasim Yousef Said
4f2e434bc3
Merge pull request #207 from unslothai/feature/attachment-restore
...
fix(chat): persist + hydrate user attachments in IndexedDB history
2026-02-21 22:09:53 -08:00
Shine1i
c726cff4c8
feat: add utils for deep cloning content and attachments in thread messages
2026-02-22 07:08:18 +01:00
Shine1i
7e1e25fb32
refactor: simplify execution overview tab by removing unused token metrics and refining layout spacing
2026-02-22 06:36:32 +01:00
Shine1i
b7dfa2b7e4
refactor: extract and modularize execution tabs and helpers for enhanced code reusability and maintainability
2026-02-22 06:26:40 +01:00
Shine1i
d6921042b0
refactor: enhance execution row handling and dataset pagination for improved interactivity and preview support
2026-02-22 05:44:23 +01:00
Shine1i
4cda750589
refactor: extract reusable runtime utilities and unify execution dialog flows for preview and full runs
2026-02-22 05:37:33 +01:00
Shine1i
17a22fe155
refactor: improve layout direction handling and auxiliary node visibility for LLMS
2026-02-22 05:18:33 +01:00
