|
--- |
|
license: other |
|
license_name: yi-34b |
|
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE |
|
--- |
|
|
|
# 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 very long context length. Model produced slight repetition, but it was very minor. I recommend testing the model to your usecase and limiting the context length. Here's my conversation: https://migel.substack.com/p/testing-tess-m-v13 |
|
|
|
As can be seen, "USER:" and "SYSTEM: Answer the question thoughtfully and intelligently. Always answer without hesitation." was presented by the model in the latter part of the conversation. |
|
|
|
# Learnings: |
|
Here's my learnings going from Tess-v1.0 to Tess-v1.3: https://migel.substack.com/p/learnings-from-training-tess |
|
|
|
# Tess |
|
|
|
 |
|
|
|
Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-M-v1.3 was trained on the Yi-34B-200K base. |
|
|
|
|
|
# Prompt Format: |
|
|
|
``` |
|
SYSTEM: <ANY SYSTEM CONTEXT> |
|
USER: |
|
ASSISTANT: |
|
``` |
|
|
|
|
