DeathReaper0965
/

flan-t5-samsum-lora-RLAIF-detoxified

Text2Text Generation

text-generation

toxicity-reduction

reinforcement-learning

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

DeathReaper0965 commited on Oct 27, 2023

Commit

c5a4336

•

1 Parent(s): f585111

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -59,7 +59,7 @@ inference:
     repetition_penalty: 10.5
     top_p: 0.95
     top_k: 50
-    temperature: 1.5
     no_repeat_ngram_size: 10
     num_return_sequences: 1
     do_sample: true

     repetition_penalty: 10.5
     top_p: 0.95
     top_k: 50
+    temperature: 1.2
     no_repeat_ngram_size: 10
     num_return_sequences: 1
     do_sample: true