Sao10K
/

MN-BackyardAI-Party-12B-v1

Model card Files Files and versions Community

Sao10K commited on Oct 1

Commit

243c5ca

•

1 Parent(s): c0fe857

Update README.md

Files changed (1) hide show

README.md +6 -5

README.md CHANGED Viewed

@@ -18,6 +18,10 @@ This model is still capable of 1 on 1 roleplay, though I recommend using ChatML
 ---
 # Formatting:
 Training for the multi-character roleplaying format is done with a variant of ChatML, replaced with [INST] blocks formatted as such. Use this to draw in more of the training done.
@@ -200,13 +204,10 @@ To make it easier, this is how I'd format responses for the backend:
 - Fantasy-bias? -> Most of the entries are fantasy-based after all.
 ```
 ---
-Training Metrics
 ```
 n_sample: 4000
 n_gpu: 2

 ---
+![party](https://huggingface.co/Sao10K/MN-BackyardAI-Party-12B-v1/resolve/main/party1.png)
+---
 # Formatting:
 Training for the multi-character roleplaying format is done with a variant of ChatML, replaced with [INST] blocks formatted as such. Use this to draw in more of the training done.
 - Fantasy-bias? -> Most of the entries are fantasy-based after all.
 ```
 ---
+# Training Metrics
 ```
 n_sample: 4000
 n_gpu: 2