cognitivecomputations
/

dolphin-2.6-mistral-7b

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

ehartford commited on Dec 28, 2023

Commit

6174913

•

1 Parent(s): 627f219

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -37,7 +37,7 @@ This model is uncensored.  I have filtered the dataset to remove alignment and b
 You are responsible for any content you create using this model.  Enjoy responsibly.
 ## Training
-It took 2 days to train 3 epochs on 4x A100s using qLoRA and Axolotl
 Prompt format:
 This model uses ChatML prompt format.  NEW - <|im_end|> maps to token_id 2. This is the same token_id as \<\/s\> so applications that depend on EOS being token_id 2 (koboldAI) will work!  (Thanks Henky for the feedback)

 You are responsible for any content you create using this model.  Enjoy responsibly.
 ## Training
+It took 2 days to train 3 epochs on 4x A100s using full weights finetune on Axolotl
 Prompt format:
 This model uses ChatML prompt format.  NEW - <|im_end|> maps to token_id 2. This is the same token_id as \<\/s\> so applications that depend on EOS being token_id 2 (koboldAI) will work!  (Thanks Henky for the feedback)