nomic-ai/gpt4all
1
1
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-11-05 04:12:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

release.json: update release notes for v3.0.0 (#2514)

Browse Source 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
Jared Van Bortel 2024-07-02 12:08:23 -04:00 committed by GitHub
parent 69102a2859
commit 1ce65e8ef2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 22 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
gpt4all-chat/metadata/release.json
View File

@ -854,8 +854,28 @@
"notes":
"
<b>&mdash; What's New &mdash;</b>
* LocalDocs Experience: Completely redesigned LocalDocs UI and backend
* New User Interface: Modern design making it easier to focus on what matters most - getting things done
* Complete UI overhaul (PR #2396)
* LocalDocs improvements (PR #2396)
* Use nomic-embed-text-v1.5 as local model instead of SBert
* Ship local model with application instead of downloading afterwards
* Store embeddings flat in SQLite DB instead of in hnswlib index
* Do exact KNN search with usearch instead of approximate KNN search with hnswlib
* Markdown support (PR #2476)
* Support CUDA/Metal device option for embeddings (PR #2477)
<b>&mdash; Fixes &mdash;</b>
* Fix embedding tokenization after PR #2310 (PR #2381)
* Fix a crash when loading certain models with \"code\" in their name (PR #2382)
* Fix an embedding crash with large chunk sizes after PR #2310 (PR #2383)
* Fix inability to load models with non-ASCII path on Windows (PR #2388)
* CUDA: Do not show non-fatal DLL errors on Windows (PR #2389)
* LocalDocs fixes (PR #2396)
* Always use requested number of snippets even if there are better matches in unselected collections
* Check for deleted files on startup
* CUDA: Fix PTX errors with some GPT4All builds (PR #2421)
* Fix blank device in UI after model switch and improve usage stats (PR #2409)
* Use CPU instead of CUDA backend when GPU loading fails the first time (ngl=0 is not enough) (PR #2477)
* Fix crash when sending a message greater than n\_ctx tokens after PR #1970 (PR #2498)
",
"contributors":
"