Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,18 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- gguf
|
5 |
+
---
|
6 |
+
GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
|
7 |
+
- Original model: [Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3)
|
8 |
+
- Model creator: [Mistral AI](https://huggingface.co/mistralai)
|
9 |
+
- [License](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md)
|
10 |
+
|
11 |
+
## Recommended Prompt Format (Mistral)
|
12 |
+
```
|
13 |
+
<s>[INST]Provide some context and/or instructions to the model.[/INST]
|
14 |
+
AI message goes here</s>
|
15 |
+
[INST] The user’s message goes here [/INST]
|
16 |
+
```
|
17 |
+
|
18 |
+
Quant Version: [b3437](https://github.com/ggerganov/llama.cpp/releases/tag/b3437) with [imatrix](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
|