Commit
•
6b0592e
1
Parent(s):
b974946
Update README.md
Browse files
README.md
CHANGED
|
@@ -196,6 +196,9 @@ extra_gated_button_content: Submit
|
|
| 196 |
|
| 197 |
# Llama.cpp imatrix quantizations of meta-llama/Meta-Llama-3.1-70B-Instruct
|
| 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](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
|
|
|
|
| 196 |
|
| 197 |
# Llama.cpp imatrix quantizations of meta-llama/Meta-Llama-3.1-70B-Instruct
|
| 198 |
|
| 199 |
+
<!-- Better pic but I would like to talk about my quants on Linkedin so yeah <img src="https://cdn-uploads.huggingface.co/production/uploads/646410e04bf9122922289dc7/xlkSJli8IQ9KoTAuTKOF2.png" alt="llama" width="30%"/> -->
|
| 200 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/646410e04bf9122922289dc7/LQUL7YII8okA8CG54mQSI.jpeg" alt="llama" width="60%"/>
|
| 201 |
+
|
| 202 |
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.
|
| 203 |
|
| 204 |
Original model: [https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
|