cicdatopea
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,7 @@
|
|
|
|
|
|
|
|
|
|
1 |
## Model Card Details
|
2 |
|
3 |
This model is an int4 model with group_size 128 and asymmetric quantization of [meta-llama/Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct) generated by [intel/auto-round](https://github.com/intel/auto-round), auto-round is needed to run this model
|
@@ -126,4 +130,4 @@ The license on this model does not constitute legal advice. We are not responsib
|
|
126 |
|
127 |
@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
|
128 |
|
129 |
-
[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- NeelNanda/pile-10k
|
4 |
+
---
|
5 |
## Model Card Details
|
6 |
|
7 |
This model is an int4 model with group_size 128 and asymmetric quantization of [meta-llama/Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct) generated by [intel/auto-round](https://github.com/intel/auto-round), auto-round is needed to run this model
|
|
|
130 |
|
131 |
@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
|
132 |
|
133 |
+
[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)
|