ModelEvalConfig
Attributes
attributemax_tokensint= 256attributetemperaturefloat= 0.0attributemax_attemptsint= 5Retries per generation call (transient inference errors).
attributebatch_sizeint= 1When >1 and the client exposes generate_batch, submit prompts in
chunks of this size and collect them concurrently. Falls back to
sequential generate calls if the client doesn't support batching.
attributeprompt_builderPromptBuilder= qwen_chat_promptFunctions
func__init__(self, max_tokens=256, temperature=0.0, max_attempts=5, batch_size=1, prompt_builder=qwen_chat_prompt) -> Noneparamselfparammax_tokensint= 256paramtemperaturefloat= 0.0parammax_attemptsint= 5parambatch_sizeint= 1paramprompt_builderPromptBuilder= qwen_chat_promptReturns
None