Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,19 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
---
|
6 |
+
|
7 |
+
This is 2-bit quantization of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) using [QuIP#](https://cornell-relaxml.github.io/quip-sharp/)
|
8 |
+
|
9 |
+
## Model loading
|
10 |
+
Please follow the instruction of [QuIP-for-all](https://github.com/chu-tianxiang/QuIP-for-all) for usage.
|
11 |
+
|
12 |
+
## Perplexity
|
13 |
+
Measured at Wikitext with 4096 context length
|
14 |
+
| fp16 | 2-bit |
|
15 |
+
| ------- | ------- |
|
16 |
+
| 3.8825 | 5.2799 |
|
17 |
+
|
18 |
+
## Speed
|
19 |
+
About 16 tokens/s at batchsize = 1 using vLLM at single A100.
|