typhoon-ai/llama3.1-typhoon2-70b-instruct
scb10x/llama3.1-typhoon2-70b-instruct is a 70 billion parameter instruction-tuned decoder-only large language model developed by scb10x, based on the Llama3.1 architecture. Optimized for Thai language performance, it excels in instruction-following, function calling, and specific domains like math and coding in both Thai and English. This model features a 90k context length, making it suitable for applications requiring extensive contextual understanding and generation in a bilingual setting.
Hugging Face Popular Sampler Settings
Most commonly used values from Featherless users
temperature
This setting influences the sampling randomness. Lower values make the model more deterministic; higher values introduce randomness. Zero is greedy sampling.
top_p
This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.
top_k
This limits the number of top tokens to consider. Set to -1 to consider all tokens.
–
frequency_penalty
This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.
–
presence_penalty
This setting penalizes new tokens based on their presence in the generated text so far. Values > 0 encourage new tokens; < 0 encourages repetition.
–
repetition_penalty
This setting penalizes new tokens based on their appearance in the prompt and generated text. Values > 1 encourage new tokens; < 1 encourages repetition.
min_p
This setting representing the minimum probability for a token to be considered relative to the most likely token. Must be in [0, 1]. Set to 0 to disable.
–