Models Qwen 272b

openthaigpt/openthaigpt1.5-72b-instruct

OpenThaiGPT 1.5 Instruct is a 72.7 billion parameter Thai language chat model developed by OpenThaiGPT, based on the Qwen v2.5 architecture. Fine-tuned on over 2,000,000 Thai instruction pairs, it excels at answering Thai-specific domain questions and achieves the highest average scores across various Thai language exams among open-source Thai LLMs. The model supports a substantial context length of up to 131,072 tokens and is designed for multi-turn conversations, RAG compatibility, and tool calling.

Cold
Public
72.7B
FP8
131072
License: qwen
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.
–