ISTA-DASLab
/

Meta-Llama-3.1-70B-AQLM-PV-2Bit-1x16

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

galqiwi commited on Sep 14

Commit

6d11ec3

•

1 Parent(s): c30d4e9

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -12,11 +12,12 @@ base_model: meta-llama/Meta-Llama-3.1-70B
 ---
 Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of [meta-llama/Meta-Llama-3.1-70B
-](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) finetuned with [PV-Tuning](https://arxiv.org/abs/2405.14852).
 For this quantization, we used 1 codebook of 16 bits and groupsize of 8.
 Results:
 | Model | Quantization | MMLU (5-shot) | ArcC   | ArcE   | Hellaswag | PiQA   | Winogrande | Model size, Gb |
 |-------|--------------|---------------|--------|--------|-----------|--------|------------|----------------|
 |       | 1x16g8       | 0.7353        | 0.4556 | 0.7731 | 0.6335	 | 0.7590 | 0.7703     | 21.9           |

 ---
 Official [AQLM](https://arxiv.org/abs/2401.06118) quantization of [meta-llama/Meta-Llama-3.1-70B
+](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct) finetuned with [PV-Tuning](https://arxiv.org/abs/2405.14852).
 For this quantization, we used 1 codebook of 16 bits and groupsize of 8.
 Results:
 | Model | Quantization | MMLU (5-shot) | ArcC   | ArcE   | Hellaswag | PiQA   | Winogrande | Model size, Gb |
 |-------|--------------|---------------|--------|--------|-----------|--------|------------|----------------|
+|       | fp16         | 0.7839        | 0.6058 | 0.8729 | 0.6650	 | 0.8292 | 0.7964     | 141            |
 |       | 1x16g8       | 0.7353        | 0.4556 | 0.7731 | 0.6335	 | 0.7590 | 0.7703     | 21.9           |