imi2
/

llama-2-7b-chat-pure-Q4_0-gguf

Model card Files Files and versions Community

imi2 commited on Apr 11

Commit

f493650

·

verified ·

1 Parent(s): 6466219

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -58,5 +58,5 @@ TODO:
 | qwen2 ?B INT_N Q4_K     | 1.70 GiB| 3.40 B | CPU     | 4       | pp512  | 59.66 ± 0.10         |
 | qwen2 ?B INT_N Q4_K     | 1.70 GiB| 3.40 B | CPU     | 4       | tg128  | 26.43 ± 0.14         |
-**It's 16.3% faster and 13% smaller.**
 - [Issue Link](https://github.com/microsoft/T-MAC/issues/79)

 | qwen2 ?B INT_N Q4_K     | 1.70 GiB| 3.40 B | CPU     | 4       | pp512  | 59.66 ± 0.10         |
 | qwen2 ?B INT_N Q4_K     | 1.70 GiB| 3.40 B | CPU     | 4       | tg128  | 26.43 ± 0.14         |
+**INT_N isn't the equivalent or a match for fair comparison. It is 16.3% faster and 13% smaller in this scenario.**
 - [Issue Link](https://github.com/microsoft/T-MAC/issues/79)