brucethemoose commited on
Commit
a90048d
1 Parent(s): ba8e2e7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -7,7 +7,7 @@ language:
7
  library_name: transformers
8
  pipeline_tag: text-generation
9
  ---
10
- NousResearch/Nous-Capybara-34B and migtissera/Tess-M-Creative-v1.0 ties merged with mergekit, then quantized with exllamav2 on 200 rows (400K tokens) on a long Vicuna format chat, a sci fi story and a fantasy story. This should yield better chat performance than the default wikitext quantization.
11
 
12
  Quantized to 4bpw, enough for **~47K context on a 24GB GPU.**
13
 
 
7
  library_name: transformers
8
  pipeline_tag: text-generation
9
  ---
10
+ Nous-Capybara-34B and Tess-M-Creative-v1.0 merged, then quantized with exllamav2 on 200 rows (400K tokens) on a long Vicuna format chat, a sci fi story and a fantasy story. This should hopefully yield better chat performance than the default wikitext quantization.
11
 
12
  Quantized to 4bpw, enough for **~47K context on a 24GB GPU.**
13