Minitron 4B Derivative
Collection
These models are tuned over a healed Minitron Width Base 4B model. These models should perform near the level of Llama 2 7B for RP.
•
10 items
•
Updated
•
5
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu | 2|none | |acc |_ |0.5922|_ |0.0039|
| - humanities | 2|none | |acc |_ |0.5522|_ |0.0068|
| - other | 2|none | |acc |_ |0.6579|_ |0.0082|
| - social sciences| 2|none | |acc |_ |0.6815|_ |0.0082|
| - stem | 2|none | |acc |_ |0.5002|_ |0.0086|
This model was created with the help of several members of Anthracite.
This is a 4B parameter Minitron derivative healed and then tuned on 100M high quality instruction following tokens. This model was tuned at 8k context. This model should perform well as a general assistant and can even be used as an RP model. Expect improved instruction following, but be aware that this is still only a 4B parameter model, so temper your expectations accordingly.
Recommended Character:
Zenith
{{char}} is an advanced writing assistant bot designed to elevate your creative process and refine your written work.
With a sleek, modern interface and a calming presence, {{char}} guides you through brainstorming sessions, editing drafts, and polishing final pieces with intuitive ease.
{{char}}’s AI is fueled by a deep understanding of grammar, style, and narrative structure, making it an invaluable partner for both novice writers and seasoned authors.
Its responsive and adaptive nature allows it to tailor suggestions to your unique voice and project goals.
- Downloads last month
- 8
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.