Unverified50% confidenceFactExact time
Common hyperparameters include temperature (controls output randomness, the lower the more deterministic), max tokens (limits generation length), top_p, and so on.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
Verified温度（temperature）参数控制采样过程，温度越高输出越随机多样，温度越低越趋向最高概率的选择75% similarUnverifiedInference parameters usually include temperature, top-p and maximum generation length; a lower temperature is conducive to code stability.75% similarUnverifiedtemperature 参数控制输出随机性，top_p 通过动态截断概率分布平衡输出多样性与质量74% similarVerifiedThe Temperature parameter of large models typically ranges from 0 to 2; the lower the temperature, the more deterministic and conservative the output, while the higher the temperature, the more diverse and creative the output.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1064077API
curl https://kongchang.com/api/v1/knowledge/claims/1064077MCP
get_claim(id=1064077)