diff options
| author | Ben Sima <ben@bsima.me> | 2024-12-02 07:52:56 -0500 |
|---|---|---|
| committer | Ben Sima <ben@bsima.me> | 2024-12-20 21:09:24 -0500 |
| commit | 18956baad9cde85bc55bd0113092e51786d9e1ee (patch) | |
| tree | 07e987380a05db04c4814f4ebbc1f5780817899c /Biz/Bild/Sources.json | |
| parent | bc78e72960dee2721c3648e8061cb543f775710b (diff) | |
Delete Biz/Mynion.py and exllama
Mynion was a prototype and while it was cool and worked well, it is unused and
causing magma to build, which takes forever. I have settled on using ollama for
local inference and a hosted inference API for production.
Diffstat (limited to 'Biz/Bild/Sources.json')
| -rw-r--r-- | Biz/Bild/Sources.json | 12 |
1 files changed, 0 insertions, 12 deletions
diff --git a/Biz/Bild/Sources.json b/Biz/Bild/Sources.json index 3b1e4fd..c12b6ce 100644 --- a/Biz/Bild/Sources.json +++ b/Biz/Bild/Sources.json @@ -25,18 +25,6 @@ "url_template": "https://github.com/<owner>/<repo>/archive/<rev>.tar.gz", "version": "0.7.0.8" }, - "exllama": { - "branch": "master", - "description": "A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.", - "homepage": null, - "owner": "jllllll", - "repo": "exllama", - "rev": "3ddf3bd39bdff330623f3740cda4ae1537ef86d9", - "sha256": "0g87xm71jmw5bl4ya5dbk72fghhhwvrjqspaayq7zass16jixr1d", - "type": "tarball", - "url": "https://github.com/jllllll/exllama/archive/3ddf3bd39bdff330623f3740cda4ae1537ef86d9.tar.gz", - "url_template": "https://github.com/<owner>/<repo>/archive/<rev>.tar.gz" - }, "ghc-exactprint": { "branch": "master", "description": "GHC version of haskell-src-exts exactPrint", |