miromind-ai/MiroThinker-4B-DPO-v0.2
MiroThinker-4B-DPO-v0.2 by miromind-ai is a 4 billion parameter open-source agentic model designed for complex, long-horizon problem solving. It integrates capabilities such as task decomposition, multi-hop reasoning, retrieval-augmented generation, code execution, web browsing, and document processing. This version features richer English and Chinese training data, unified DPO training, and an extended 40960-token context length, showing significant gains in research agent benchmarks like GAIA-Text-103 and BrowseComp-ZH.
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.
–