Hugging Face's logo

MatrixC7
/
karakuri-lm-70b-v0.1-exl2

Text Generation
Japanese
English
llama
llama-2
Model card Files Community
1
MatrixC7 commited on
Commit
2ccc3b3
•
1 Parent(s): 9d1ea95

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -35,4 +35,4 @@ The chart below presents the calibration perplexity and [wikitext-103-v1](https:
35
  | [6.0bpw-h6](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/6.0bpw-h6) | 7.5616 | |
36
  | [8.0bpw-h8](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/8.0bpw-h8) | 7.5604 | |
37
 
38
- *: This first version has been deprecated due to unexpectedly high wikitext-103-v1 Test Perplexity values.
 
35
  | [6.0bpw-h6](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/6.0bpw-h6) | 7.5616 | |
36
  | [8.0bpw-h8](https://huggingface.co/MatrixC7/karakuri-lm-70b-v0.1-exl2/tree/8.0bpw-h8) | 7.5604 | |
37
 
38
+ *: This first 2.65bpw-h6 quantized version has been deprecated due to unexpectedly high wikitext-103-v1 Test Perplexity values.