Update README.md
Browse files
README.md
CHANGED
|
@@ -23,7 +23,6 @@ CodeFuse-CodeLlama-34B-4bits is the 4-bit quantized version of CodeFuse-CodeLlam
|
|
| 23 |
|
| 24 |
After undergoing 4-bit quantization, the CodeFuse-CodeLlama-34B-4bits model can be loaded on either a single A10 (24GB VRAM) or a RTX 4090 (24GB VRAM). Moreover, the quantized model still achives an impressive accuracy of 73.8% on the Humaneval pass@1 metric.
|
| 25 |
|
| 26 |
-
|
| 27 |
<br>
|
| 28 |
|
| 29 |
## News and Updates
|
|
@@ -205,8 +204,6 @@ Here, SHA256 values are provided for the model-related files for consistency che
|
|
| 205 |
|tokenizer.model | 9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 |
|
| 206 |
|tokenizer_config.json | c12441e82f2dce0baff87cf5948e82d6e9b51cc0b5266369c30c319fb771eeb2 |
|
| 207 |
|
| 208 |
-
|
| 209 |
-
<br>
|
| 210 |
<br>
|
| 211 |
|
| 212 |
## Citation
|
|
@@ -221,6 +218,7 @@ If you find our [work](https://arxiv.org/abs/2311.02303) useful or helpful for y
|
|
| 221 |
eprint={2311.02303}
|
| 222 |
}
|
| 223 |
```
|
|
|
|
| 224 |
|
| 225 |
<a id="chinese"></a>
|
| 226 |
|
|
|
|
| 23 |
|
| 24 |
After undergoing 4-bit quantization, the CodeFuse-CodeLlama-34B-4bits model can be loaded on either a single A10 (24GB VRAM) or a RTX 4090 (24GB VRAM). Moreover, the quantized model still achives an impressive accuracy of 73.8% on the Humaneval pass@1 metric.
|
| 25 |
|
|
|
|
| 26 |
<br>
|
| 27 |
|
| 28 |
## News and Updates
|
|
|
|
| 204 |
|tokenizer.model | 9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 |
|
| 205 |
|tokenizer_config.json | c12441e82f2dce0baff87cf5948e82d6e9b51cc0b5266369c30c319fb771eeb2 |
|
| 206 |
|
|
|
|
|
|
|
| 207 |
<br>
|
| 208 |
|
| 209 |
## Citation
|
|
|
|
| 218 |
eprint={2311.02303}
|
| 219 |
}
|
| 220 |
```
|
| 221 |
+
<br>
|
| 222 |
|
| 223 |
<a id="chinese"></a>
|
| 224 |
|