radlab
/

pLLama3.2-3B-DPO

Model card Files Files and versions Community

pLLama3.2-3B-DPO / README.md

pkedzia's picture

Update README.md

35c105a verified 4 months ago

|

83 Bytes

metadata

license: llama3.2

Parameters:

temperature: 0.6
repetition_penalty: 1.0