Subtext Labs - Official Model Releases
Collection
2 items
•
Updated
Llama3 8B Wordcel
Wordcel is a Llama3 fine-tune intended to be used as a mid-training checkpoint for more specific RP/storywriting/creative applications.
It has been trained from Llama3 8B Base on a composite dataset of ~100M tokens that highlights reasoning, (uncensored) stories, classic literature, and assorted interpersonal intelligence tasks.
Components of the composite dataset include OpenHermes-2.5, and Grimulkan's Theory of Mind and Physical Reasoning datasets.
It is trained at a context length of 32k tokens, using linear RoPE scaling with a factor of 4.0. Derivative models should be capable of generalizing to 32k tokens as a result.
If you train a model using this checkpoint, please give clear attribution! The Llama 3 base license likely applies.
- Downloads last month
- 29
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.