Text Generation
Transformers
Safetensors
English
qwen2
conversational
text-generation-inference

What is the best sampling config?

#1
by pootow - opened

What is the best value for temperature, top_k, top_p, etc.?

Agentica org

We recommend:

  • top_p= 0.95
  • temperature = 0.6
  • max_tokens = 64000
alpayariyak changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment