Roland Tannous
|
7bc235bed2
|
Merge branch 'nightly' into feature/windows-native-support
|
2026-03-03 22:23:18 +04:00 |
|
Roland Tannous
|
a4d2853fbc
|
fix: align llama-server binary discovery with upstream unsloth-zoo paths
|
2026-03-03 17:03:01 +00:00 |
|
Roland Tannous
|
e280e457d1
|
Move llama.cpp clone/build from in-tree to ~/.unsloth/llama.cpp
- setup.sh: builds at ~/.unsloth/llama.cpp instead of ./llama.cpp
- setup.ps1: builds at %USERPROFILE%/.unsloth/llama.cpp
- inference llama_cpp.py: searches ~/.unsloth/ first, in-tree as legacy
- export.py: updated comments (unsloth-zoo handles path natively)
|
2026-03-02 04:04:41 +00:00 |
|
Wasim Yousef Said
|
dc7976c534
|
Merge pull request #294 from unslothai/fix/navbar-center-tabs-shift
Prevent navbar tab shift when navigating across pages
|
2026-03-01 15:42:19 +01:00 |
|
Wasim Yousef Said
|
2df2d671ce
|
Merge pull request #290 from unslothai/fix/model-dropdown-visual-consistency
Standard OOM/TIGHT model status indicators across model dropdowns
|
2026-03-01 15:41:39 +01:00 |
|
Roland Tannous
|
6e5a3d1744
|
Download GGUF via huggingface_hub instead of llama-server -hf (fixes HTTPS not supported on Windows)
|
2026-03-01 13:05:10 +00:00 |
|
Roland Tannous
|
12867f701b
|
Auto-add CUDA DLLs to PATH when launching llama-server on Windows
|
2026-03-01 13:05:10 +00:00 |
|
Roland Tannous
|
3521de7040
|
Build llama.cpp in-tree, auto-detect driver CUDA version for compatible toolkit
|
2026-03-01 13:05:10 +00:00 |
|
Roland Tannous
|
f036a70681
|
Fix llama-server binary lookup for Windows (.exe, Release dir, ~/.unsloth)
|
2026-03-01 13:05:10 +00:00 |
|
Roland Tannous
|
7e021886c8
|
Force num_proc=1 on Windows to avoid slow spawn overhead
|
2026-03-01 13:05:10 +00:00 |
|
Roland Tannous
|
ff93c97024
|
fix: support mmproj for local vision GGUF models + fix Windows pipe deadlock
|
2026-03-01 12:58:38 +00:00 |
|
imagineer99
|
471fc8fd90
|
fix: prevent navbar tab shift when navigating across pages
|
2026-03-01 03:02:49 +00:00 |
|
imagineer99
|
42f5ba5fcc
|
fix: standardize OOM/TIGHT model status indicators across model dropdowns
|
2026-03-01 00:02:15 +00:00 |
|
Shine1i
|
ce33d673b9
|
feat(markdown): fix Mermaid integration with error handling and copy button
|
2026-02-27 20:02:40 +01:00 |
|
Roland Tannous
|
89d0a98192
|
Merge pull request #284 from unslothai/fix/drop-model-task-hard-filter
Apply HF task filtering only for empty model queries
|
2026-02-27 15:46:17 +04:00 |
|
imagineer99
|
49c319c2f7
|
fix: only apply HF task filter for empty model search queries
|
2026-02-27 11:31:53 +00:00 |
|
Wasim Yousef Said
|
ad7c1ceb40
|
Merge pull request #268 from unslothai/fix/delete-custom-config
Updated the delete custom preset in chat tab (filters)
|
2026-02-27 01:38:01 -08:00 |
|
Shine1i
|
6d74943dea
|
keep checkpoint on preset apply
|
2026-02-27 10:36:07 +01:00 |
|
Wasim Yousef Said
|
7c364b594c
|
Merge pull request #269 from unslothai/fix/fine-tuned-model-tooltip
Added tooltip for the fine tuned models in chat page
|
2026-02-27 01:34:49 -08:00 |
|
Shine1i
|
3c728f5eb3
|
merge nightly
|
2026-02-27 10:31:37 +01:00 |
|
Roland Tannous
|
6e12e2536d
|
Merge pull request #267 from unslothai/fix/config-switch
Preserving model name during configuration type switch in chat page
|
2026-02-27 13:23:29 +04:00 |
|
Roland Tannous
|
5be7ae925d
|
Merge pull request #266 from unslothai/fix/dataset-search-remove-size-download-badges
Remove dataset metadata badges from HF dataset dropdowns
|
2026-02-27 13:22:49 +04:00 |
|
Roland Tannous
|
cef36ee8e8
|
Merge pull request #282 from unslothai/fix/inference-auth
Added auth to inference endpoints
|
2026-02-27 13:18:38 +04:00 |
|
Roland Tannous
|
32d68b99e3
|
Merge pull request #278 from unslothai/fix/reorder-model-type-cards-onboarding
Reorder model type cards in onboarding to show Text first
|
2026-02-27 13:17:00 +04:00 |
|
Manan17
|
168957a87a
|
Aggregating sharded models, showing fit/oom for quantizations
|
2026-02-27 08:23:15 +00:00 |
|
samit
|
b18a14d369
|
added auth to inference endpoints
|
2026-02-27 00:20:36 -08:00 |
|
Manan17
|
2fea4cadd3
|
Passes metadata to get model size
|
2026-02-27 07:38:55 +00:00 |
|
imagineer99
|
4aecfb80d4
|
fix: reorder model type cards in onboarding to show Text first
|
2026-02-27 06:16:26 +00:00 |
|
Shine1i
|
00a869f837
|
refactor(data-recipe): centralize json+stage constants, tighten parser/errors, sync seed ui
|
2026-02-26 14:06:53 +01:00 |
|
Shine1i
|
e4b64f3cd5
|
refactor(data-recipe): split recipe backend routes for readability (seed/validate/jobs)
|
2026-02-26 14:05:32 +01:00 |
|
Shine1i
|
aaf62095fe
|
feat(recipe-studio): add jinja ref validation UI for llm/expression fields
|
2026-02-26 13:35:07 +01:00 |
|
Shine1i
|
1e3d50f876
|
feat(recipe-studio): add block sheet search + clearer icons in sheet
|
2026-02-26 12:55:09 +01:00 |
|
Shine1i
|
81a7e38aa6
|
chore: simplify recipe drag payload parsing
|
2026-02-26 12:48:04 +01:00 |
|
Shine1i
|
9ee7633bc1
|
feat(recipe-studio): add sidebar drag-drop block creation + spawn sheet added blocks at viewport center
|
2026-02-26 12:45:38 +01:00 |
|
Shine1i
|
04d6f5e67b
|
feat(recipe-studio): sanitize shared seed payload + add inline seed UX with HF search
|
2026-02-26 12:23:05 +01:00 |
|
Shine1i
|
75857cdcea
|
feat(recipe-studio): polish import/llm editors, refs preview, copy toast, and note layout behavior
|
2026-02-26 11:44:57 +01:00 |
|
Shine1i
|
a53d8cb272
|
fix(recipe-studio): preserve note positions during auto-layout and fit workflow only
|
2026-02-26 11:30:24 +01:00 |
|
Shine1i
|
d1047646a9
|
feat(recipe-studio): optimize model infra auto-layout handles and centering
|
2026-02-26 11:07:07 +01:00 |
|
Shine1i
|
dd3e1e7293
|
refactor(recipe-studio): simplify aux node graph logic and remove dead handle/sync code
|
2026-02-26 10:43:26 +01:00 |
|
Shine1i
|
48f7d40e87
|
feat(ui): normalize recipe dialogs + chip/category UX polish
|
2026-02-26 10:13:01 +01:00 |
|
Shine1i
|
1de4b73244
|
fix: recipe studio dialog combobox click-select + simplify model provider form
|
2026-02-26 10:03:47 +01:00 |
|
Roland Tannous
|
28e0218263
|
Merge pull request #270 from unslothai/fix/gguf-export-relocation
Fix GGUF exports saving to wrong directory and missing from chat model selector
|
2026-02-26 11:48:15 +04:00 |
|
Roland Tannous
|
ed18f9b9dd
|
Flatten GGUF subdirs in export and fix metadata lookup in scanner
|
2026-02-26 11:35:04 +04:00 |
|
Roland Tannous
|
90f012a444
|
Write export metadata for GGUF exports to fix Unknown base model
|
2026-02-26 11:24:32 +04:00 |
|
Roland Tannous
|
2ce63f09c4
|
Add gguf to toLoraSummary inline type
|
2026-02-26 10:59:39 +04:00 |
|
Roland Tannous
|
609ae4809a
|
Merge pull request #229 from unslothai/feat/dataset-list-sorting
Feat: Sort and filter dataset search results by model type relevance
|
2026-02-26 10:40:02 +04:00 |
|
Roland Tannous
|
ea9b22000e
|
Merge pull request #245 from unslothai/fix/datetime-utc-python39-compatibility
fix: replace datetime.UTC with timezone.utc for Python 3.9+ compatibility
|
2026-02-26 10:37:01 +04:00 |
|
imagineer99
|
852dff564e
|
feat: added datasets of size 5M and 10M to pretraining size category
|
2026-02-26 06:32:45 +00:00 |
|
imagineer99
|
6e535ed0eb
|
fix: filter OCR datasets from non-vision hub results
|
2026-02-26 06:27:52 +00:00 |
|
samit
|
04aee4a4c6
|
updated to make the delete preset work
|
2026-02-25 21:36:50 -08:00 |
|