ThomasBaruzier
commited on
Commit
•
38571e2
1
Parent(s):
cbea6b0
Update README.md
Browse files
README.md
CHANGED
@@ -198,7 +198,7 @@ extra_gated_button_content: Submit
|
|
198 |
|
199 |
Using llama.cpp commit [b5e9546](https://github.com/ggerganov/llama.cpp/commit/b5e95468b1676e1e5c9d80d1eeeb26f542a38f42) for quantization, featuring llama 3.1 rope scaling factors. This fixes low-quality issues when using 8-128k context lengths.
|
200 |
|
201 |
-
Original model:
|
202 |
|
203 |
All quants were made using the imatrix option and Bartowski's [calibration file](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8).
|
204 |
|
|
|
198 |
|
199 |
Using llama.cpp commit [b5e9546](https://github.com/ggerganov/llama.cpp/commit/b5e95468b1676e1e5c9d80d1eeeb26f542a38f42) for quantization, featuring llama 3.1 rope scaling factors. This fixes low-quality issues when using 8-128k context lengths.
|
200 |
|
201 |
+
Original model: https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct
|
202 |
|
203 |
All quants were made using the imatrix option and Bartowski's [calibration file](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8).
|
204 |
|