Add model card
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
tags:
|
| 3 |
+
- quantized
|
| 4 |
+
- 4-bit
|
| 5 |
+
- AWQ
|
| 6 |
+
- autotrain_compatible
|
| 7 |
+
- endpoints_compatible
|
| 8 |
+
- text-generation-inference
|
| 9 |
license: apache-2.0
|
| 10 |
+
language:
|
| 11 |
+
- en
|
| 12 |
+
base_model: mistral-community/Mixtral-8x22B-v0.1
|
| 13 |
+
model_creator: Vezora
|
| 14 |
+
model_name: Mistral-22B-v0.1
|
| 15 |
+
model_type: mistral
|
| 16 |
+
pipeline_tag: text-generation
|
| 17 |
+
inference: false
|
| 18 |
---
|
| 19 |
+
# Vezora/Mistral-22B-v0.1 AWQ
|
| 20 |
+
|
| 21 |
+
- Model creator: [Vezora](https://huggingface.co/Vezora)
|
| 22 |
+
- Original model: [Mistral-22B-v0.1](https://huggingface.co/Vezora/Mistral-22B-v0.1)
|
| 23 |
+
|
| 24 |
+
## Model Summary
|
| 25 |
+
|
| 26 |
+
This model is not an moe, it is infact a 22B parameter dense model!
|
| 27 |
+
|
| 28 |
+
Just one day after the release of **Mixtral-8x-22b**, we are excited to introduce our handcrafted experimental model, **Mistral-22b-V.01**. This model is a culmination of equal knowledge distilled from all experts into a single, dense 22b model. This model is not a single trained expert, rather its a compressed MOE model, turning it into a dense 22b mode. This is the first working MOE to Dense model conversion.
|
| 29 |
+
|