bartowski commited on
Commit
d436c9e
·
1 Parent(s): 32b3d87

Update readme with 8.0 link

Browse files
Files changed (1) hide show
  1. README.md +1 -4
README.md CHANGED
@@ -1,5 +1,2 @@
1
- ## Exllama v2 Quantization of Mistral-7B-codealpaca-lora
2
 
3
- Conversion done using evol-codealpaca-v1.parquet as calibration dataset.
4
-
5
- Original model: https://huggingface.co/Nondzu/Mistral-7B-codealpaca-lora
 
 
1
 
2
+ <a href="base_quant_repo_url/tree/8.0">8.0 bits per weight</a>