Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,28 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
+
|
5 |
+
## Q8-GGUF for [migtissera/Tess-XS-v1-3-yarn-128K ](https://huggingface.co/migtissera/Tess-XS-v1-3-yarn-128K)
|
6 |
+
|
7 |
+
|
8 |
+
# Note:
|
9 |
+
This version is the stable release. The issues that were present in versions 1.0, 1.1 and 1.2 all have been rectified. Thank you for your patience while R&D was conducted. Enjoy!
|
10 |
+
|
11 |
+
This model have been tested on context length up to 16K. Model produced slight repetition around 16K context length. I recommend testing the model to your usecase and limiting the context length.
|
12 |
+
|
13 |
+
Here's my learnings going from Tess-v1.0 to Tess-v1.3: https://migel.substack.com/p/learnings-from-training-tess
|
14 |
+
|
15 |
+
# Tess
|
16 |
+
|
17 |
+
![Tess](https://huggingface.co/migtissera/Tess-M-v1.0/resolve/main/Tess.png)
|
18 |
+
|
19 |
+
Tess, short for Tessoro/Tessoso, is a general purpose Large Language Model series. Tess-XS-v1.3 was trained on the Nous Research Mistral-7B-yarn-128K base.
|
20 |
+
|
21 |
+
|
22 |
+
# Prompt Format:
|
23 |
+
|
24 |
+
```
|
25 |
+
SYSTEM: <ANY SYSTEM CONTEXT>
|
26 |
+
USER:
|
27 |
+
ASSISTANT:
|
28 |
+
```
|