Update README.md
Browse files
README.md
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
---
|
|
|
2 |
library_name: transformers
|
3 |
tags:
|
4 |
- 4-bit
|
@@ -15,7 +16,27 @@ quantized_by: Suparious
|
|
15 |
- Model creator: [migtissera](https://huggingface.co/migtissera)
|
16 |
- Original model: [Tess-2.0-Llama-3-8B](https://huggingface.co/migtissera/Tess-2.0-Llama-3-8B)
|
17 |
|
|
|
18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## How to use
|
21 |
|
|
|
1 |
---
|
2 |
+
license: llama3
|
3 |
library_name: transformers
|
4 |
tags:
|
5 |
- 4-bit
|
|
|
16 |
- Model creator: [migtissera](https://huggingface.co/migtissera)
|
17 |
- Original model: [Tess-2.0-Llama-3-8B](https://huggingface.co/migtissera/Tess-2.0-Llama-3-8B)
|
18 |
|
19 |
+
![Tesoro](https://huggingface.co/migtissera/Tess-2.0-Mixtral-8x22B/resolve/main/Tess-2.png)
|
20 |
|
21 |
+
## Model Summary
|
22 |
+
|
23 |
+
Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-2.0-Llama-3-8B was trained on the meta-llama/Meta-Llama-3-8B base.
|
24 |
+
|
25 |
+
### Prompt Format
|
26 |
+
|
27 |
+
Prompt format used for this fine-tune is Llama-3
|
28 |
+
|
29 |
+
```
|
30 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
31 |
+
|
32 |
+
You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>
|
33 |
+
|
34 |
+
Who are you?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
35 |
+
|
36 |
+
I am an AI<|eot_id|><|start_header_id|>user<|end_header_id|>
|
37 |
+
|
38 |
+
What's your name?<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
39 |
+
```
|
40 |
|
41 |
## How to use
|
42 |
|