Update README.md
Browse files
README.md
CHANGED
|
@@ -10,8 +10,6 @@ tags:
|
|
| 10 |
- moe
|
| 11 |
---
|
| 12 |
# Model Card for Mixtral-8x22B
|
| 13 |
-
This repo is derived from the full-precision model here: [v2ray/Mixtral-8x22B-v0.1](https://huggingface.co/v2ray/Mixtral-8x22B-v0.1), you can download from there if you want to. \
|
| 14 |
-
|
| 15 |
The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.
|
| 16 |
|
| 17 |
Model details:
|
|
@@ -21,6 +19,9 @@ Model details:
|
|
| 21 |
- 🤓 32K vocab size
|
| 22 |
- ✂️ Similar tokenizer as 7B
|
| 23 |
|
|
|
|
|
|
|
|
|
|
| 24 |
## Run the model in 4-bit precision
|
| 25 |
```python
|
| 26 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
| 10 |
- moe
|
| 11 |
---
|
| 12 |
# Model Card for Mixtral-8x22B
|
|
|
|
|
|
|
| 13 |
The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.
|
| 14 |
|
| 15 |
Model details:
|
|
|
|
| 19 |
- 🤓 32K vocab size
|
| 20 |
- ✂️ Similar tokenizer as 7B
|
| 21 |
|
| 22 |
+
Model quantized and added by [Prince Canuma](https://twitter.com/Prince_Canuma) using the full-precision model here: [v2ray/Mixtral-8x22B-v0.1](https://huggingface.co/v2ray/Mixtral-8x22B-v0.1).
|
| 23 |
+
|
| 24 |
+
|
| 25 |
## Run the model in 4-bit precision
|
| 26 |
```python
|
| 27 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|