jukofyork commited on
Commit
ff3fb58
1 Parent(s): 290cccd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -9,6 +9,6 @@ tags:
9
 
10
  An experimental model, fine-tuned using the "multiplicative-LoRA" method on [c4ai-command-r-v01](https://huggingface.co/CohereForAI/c4ai-command-r-v01).
11
 
12
- This model is nearly identical to [creative-writer-v0.1-bravo-35b](https://huggingface.co/jukofyork/creative-writer-v0.1-bravo-35b) (ie: the pre-softmax logits were scaled by `1.1` during training to increased single-token Entropy), but uses the new `v0.2` dataset which is around 15% larger and also more carefully curated to remove any weird formatting.
13
 
14
  Please refer to [creative-writer-v0.1-alfa-35b](https://huggingface.co/jukofyork/creative-writer-v0.1-alfa-35b) for full details on how to use this model.
 
9
 
10
  An experimental model, fine-tuned using the "multiplicative-LoRA" method on [c4ai-command-r-v01](https://huggingface.co/CohereForAI/c4ai-command-r-v01).
11
 
12
+ This model is nearly identical to [creative-writer-v0.1-bravo-35b](https://huggingface.co/jukofyork/creative-writer-v0.1-bravo-35b) (ie: the pre-softmax logits were scaled by `1.1` during training to increased single-token Entropy), but trained using the new `v0.2` dataset which is around 15% larger and also more carefully curated to remove any weird formatting.
13
 
14
  Please refer to [creative-writer-v0.1-alfa-35b](https://huggingface.co/jukofyork/creative-writer-v0.1-alfa-35b) for full details on how to use this model.