You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In the docs, it specifies that length_penalty is only for beam search - that means that in multinomial sampling, length_penalty does not change the generation.
* @param length_penalty exponential penalty to the length that is used with beam-based generation. It is applied as an exponent to
It would be useful if length_penalty could be used in combination with max_length or max_new_tokens in order to scale the importance of the eos token during multinomial sampling, then it would help to get prompt results that end more naturally as the max_length limit approaches.
The text was updated successfully, but these errors were encountered:
@sbalandi, is length_penalty applied to greedy and multinational after the implementation switched to the Sampler? If so, please update doc strings for C++ and Python.
In the docs, it specifies that length_penalty is only for beam search - that means that in multinomial sampling, length_penalty does not change the generation.
openvino.genai/src/cpp/include/openvino/genai/generation_config.hpp
Line 51 in 7954d82
It would be useful if length_penalty could be used in combination with max_length or max_new_tokens in order to scale the importance of the eos token during multinomial sampling, then it would help to get prompt results that end more naturally as the max_length limit approaches.
The text was updated successfully, but these errors were encountered: