Hugging Face's logo

migtissera
/
Tess-XS-v1-3-yarn-128K

Text Generation
Transformers
PyTorch
mistral
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
1
Tess-XS-v1-3-yarn-128K / README.md
migtissera's picture
migtissera
Update README.md
72d393d
preview code
|
raw
history blame
No virus
859 Bytes
metadata
license: apache-2.0

Note:

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!

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.

Here's my learnings going from Tess-v1.0 to Tess-v1.3: https://migel.substack.com/p/learnings-from-training-tess

Tess

Tess

Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-XS-v1.3 was trained on the Nous Research Mistral-7B-yarn-128K base.

Prompt Format: 

SYSTEM: <ANY SYSTEM CONTEXT>
USER: 
ASSISTANT: