Commit
•
83cebf8
1
Parent(s):
aefc57c
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,13 +6,13 @@ Selected evaluation results for this and other models:
|
|
| 6 |
|
| 7 |
| Model | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link |
|
| 8 |
|------------|-------------|----------------|----------------|--------------------------------------------------------------------------|
|
| 9 |
-
| Llama-2-7b
|
| 10 |
-
| Llama-2-7b
|
| 11 |
-
| Llama-2-7b
|
| 12 |
-
| Llama-2-13b (THIS)| 1x16 | 5.22 | 4.1 | [Link](https://huggingface.co/
|
| 13 |
-
| Llama-2-70b| 1x16 | 3.
|
| 14 |
-
| Llama-2-70b| 2x8 | 4.
|
| 15 |
-
| Mixtral-8x7b| 1x16 |
|
| 16 |
-
| Mixtral-8x7b-Instruct| 1x16 | - | 12.6 | [Link](https://huggingface.co/
|
| 17 |
|
| 18 |
To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the [official GitHub repo](https://github.com/Vahe1994/AQLM).
|
|
|
|
| 6 |
|
| 7 |
| Model | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link |
|
| 8 |
|------------|-------------|----------------|----------------|--------------------------------------------------------------------------|
|
| 9 |
+
| Llama-2-7b | 1x16 | 5.92 | 2.4 | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-7b-AQLM-2Bit-1x16-hf) |
|
| 10 |
+
| Llama-2-7b | 2x8 | 6.69 | 2.2 | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf) |
|
| 11 |
+
| Llama-2-7b | 8x8 | 6.61 | 2.2 | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-7b-AQLM-2Bit-8x8-hf) |
|
| 12 |
+
| Llama-2-13b (THIS) | 1x16 | 5.22 | 4.1 | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-13b-AQLM-2Bit-1x16-hf)|
|
| 13 |
+
| Llama-2-70b| 1x16 | 3.83 | 18.8 | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-70b-AQLM-2Bit-1x16-hf)|
|
| 14 |
+
| Llama-2-70b| 2x8 | 4.21 | 18.2 | [Link](https://huggingface.co/ISTA-DASLab/Llama-2-70b-AQLM-2Bit-2x8-hf) |
|
| 15 |
+
| Mixtral-8x7b| 1x16 | 3.35 | 12.6 | [Link](https://huggingface.co/ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf)|
|
| 16 |
+
| Mixtral-8x7b-Instruct| 1x16 | - | 12.6 | [Link](https://huggingface.co/ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf)|
|
| 17 |
|
| 18 |
To learn more about the inference, as well as the information on how to quantize models yourself, please refer to the [official GitHub repo](https://github.com/Vahe1994/AQLM).
|