Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
pipeline_tag: text-generation
|
|
|
4 |
tags:
|
5 |
- transformers
|
6 |
- safetensors
|
@@ -17,12 +18,15 @@ quantized_by: Suparious
|
|
17 |
---
|
18 |
# mistralai/Mistral-7B-v0.2 AWQ
|
19 |
|
20 |
-
|
|
|
21 |
|
22 |
## Model Summary
|
23 |
|
24 |
Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1
|
25 |
|
|
|
|
|
26 |
- 32k context window (vs 8k context in v0.1)
|
27 |
- Rope-theta = 1e6
|
28 |
- No Sliding-Window Attention
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
pipeline_tag: text-generation
|
4 |
+
base_model: mistral-community/Mistral-7B-v0.2
|
5 |
tags:
|
6 |
- transformers
|
7 |
- safetensors
|
|
|
18 |
---
|
19 |
# mistralai/Mistral-7B-v0.2 AWQ
|
20 |
|
21 |
+
- Model creator: [mistral-community](https://huggingface.co/mistral-community)
|
22 |
+
- Original model: [Mistral-7B-v0.2](https://huggingface.co/mistral-community/Mistral-7B-v0.2)
|
23 |
|
24 |
## Model Summary
|
25 |
|
26 |
Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1
|
27 |
|
28 |
+
|
29 |
+
|
30 |
- 32k context window (vs 8k context in v0.1)
|
31 |
- Rope-theta = 1e6
|
32 |
- No Sliding-Window Attention
|