Featherless
GenesisGeoZJUVAI
Start Chat
0.8B Params BF16 Open Weights Inference Available

ZJUVAI/GenesisGeo is a 0.8 billion parameter language model, built upon the Qwen3-0.6B-Base architecture, specialized in automated geometric theorem proving. It is fine-tuned to propose auxiliary constructions for challenging geometry problems, forming the core of the GenesisGeo neuro-symbolic system. Trained on 21.8 million synthetic geometric theorems, it demonstrates strong performance in geometric reasoning tasks, achieving 24/30 problems solved on the IMO-AG-30 benchmark.

Loading preview...

Parameters:0.8BContext length:32kArchitecture:TransformerPrecision:BF16Quantized variants:AvailableLast updated:September 2025
0.0M
0.0K

Model tree for

ZJUVAI/GenesisGeo
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.

–