ivabus/pantry
1
0
Fork 0
mirror of https://github.com/ivabus/pantry synced 2024-09-20 16:50:50 +03:00
Code Issues Actions Packages Projects Releases Wiki Activity
2464 commits 3 branches 0 tags 6.3 MiB
Commit graph

16 commits

Author SHA1 Message Date
Max Howell 2c4fedb117 fix whisper.cpp metal; remove helpers 
Trying to standardize on huggingface-cli downloads the models and ScriptHub scripts or endpoints make use of that.
 2023-11-22 07:06:56 -05:00
Jacob Heider 0541068b8b fix(whisper.cpp) 
closes #3981
 2023-11-07 14:50:23 -05:00
Jacob Heider 3adaa94a1f fix(llama.cpp) 
closes #3915
closes #3917
closes #3919
closes #3923
closes #3924
closes #3926
closes #3927
closes #3928
closes #3929
closes #3931
 2023-11-01 23:19:54 -04:00
Max Howell a5a1bd7b12
Use recommended model 2023-10-26 14:29:00 -04:00
Max Howell a40a0d8fc8
fix llama.cpp model download 2023-10-26 08:13:43 -04:00
James Reynolds 2b06942c62
GitHub.com/ggerganov/llama.cpp update (#3696) 
* llama.cpp, github version instead of hardcoded version
* llama.cpp, check if model is specified, if yes, run it, if not, then download model
* Use entrypoint for custom llama.cpp invocation
* `llama.cpp` is just raw executable. This I think is our new pattern.
* To run chat use the entrypoint: `pkgx +brewkit -- run llama.cpp`

Co-authored-by: James Reynolds <magnsuviri@me.com>
Co-authored-by: Max Howell <mxcl@me.com>
 2023-10-26 07:24:04 -04:00
Jacob Heider 587441621e
don't use python3.12 widely yet 2023-10-03 11:23:56 -04:00
Max Howell 81e7a5e16f
pkgx 2023-10-01 14:44:42 -04:00
Max Howell 9c56216f04
entrypoint for agpt.co 2023-07-30 08:01:11 -04:00
Max Howell 1554f7e49d
fix model download url 2023-07-24 16:54:33 -04:00
Max Howell 7c803208a2
update llama.cpp; use OpenLLaMA (#2655) 2023-07-24 16:43:32 -04:00
Sanchit Ram Arvind 90fe423a3e
libsdl dependency (#1966) 
* libsdl dependency

* remove redundant dependency

---------

Co-authored-by: Jacob Heider <jacob@tea.xyz>
 2023-05-14 00:16:14 -04:00
Sanchit Ram Arvind ea39f209ca
+whisper.cpp (#1276) 
Co-authored-by: Max Howell <mxcl@me.com>
 2023-05-04 17:49:17 -03:00
James Reynolds 9ef056e74a Updated to 2023.04.11 8b67998 2023-04-13 07:52:27 -04:00
Max Howell 96857e732b +llama.cpp 2023-03-28 08:48:03 -04:00
Max Howell d8a3e7c646
+llama.cpp (#844) 
llama.cpp -p "Getting paid to write open source can be accomplished in 3 simple steps:"
 2023-03-24 17:53:39 -04:00