Update README.md
Browse files
README.md
CHANGED
|
@@ -15,8 +15,9 @@ license_name: llama3
|
|
| 15 |
|
| 16 |
# Quant Infos
|
| 17 |
|
| 18 |
-
##
|
| 19 |
|
|
|
|
| 20 |
- Updated for latest bpe pre-tokenizer fixes https://github.com/ggerganov/llama.cpp/pull/6920
|
| 21 |
- quants done with an importance matrix for improved quantization loss
|
| 22 |
- K & IQ quants in basically all variants from Q6_K down to IQ1_S
|
|
|
|
| 15 |
|
| 16 |
# Quant Infos
|
| 17 |
|
| 18 |
+
## Based on newest(2024/05/03) quant version
|
| 19 |
|
| 20 |
+
- Requantized for newer updates quants from 2024/05/03.
|
| 21 |
- Updated for latest bpe pre-tokenizer fixes https://github.com/ggerganov/llama.cpp/pull/6920
|
| 22 |
- quants done with an importance matrix for improved quantization loss
|
| 23 |
- K & IQ quants in basically all variants from Q6_K down to IQ1_S
|