Downloads · 30 days
30
0% of all-time downloads
Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16
ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16
Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 is a text generation model from ISTA-DASLab. Use it when you need the model to write or continue text. It is set up for transformers.
Official AQLM quantization of meta-llama/Meta-Llama-3-70B-Instruct .
All-time downloads
8.7K
Public
Parameters
11B
21.9 GB on disk
Likes
20
Public
Repo makeup
Click a slice to open those files.
.safetensors21.9 GB · 100%
Parameter types
How the weights are stored.
I168.6B · 78%
Try a prompt
Model card
From the Hugging Face model README
Official AQLM quantization of meta-llama/Meta-Llama-3-70B-Instruct .
For this quantization, we used 1 codebook of 16 bits.
Results (measured with lm_eval==4.0):
| Model | Quantization | MMLU (5-shot) | ArcC | ArcE | Hellaswag | Winogrande | PiQA | Model size, Gb |
|---|---|---|---|---|---|---|---|---|
| meta-llama/Meta-Llama-3-70B | - | 0.7980 | 0.6160 | 0.8624 | 0.6367 | 0.8183 | 0.7632 | 141.2 |
| 1x16 | 0.7587 | 0.4863 | 0.7668 | 0.6159 | 0.7481 | 0.7537 | 21.9 |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- May 3, 2024
- Updated
- May 13, 2024