DedeProGames/ open-reasoner2:0.8b

25 2 days ago

OpenReasoner is a fine-tuned model from the Qwen3.5 family, trained on three reasoning datasets.

vision tools thinking 0.8b 9b
... /
params
9371364b27a5 · 65B
{
"presence_penalty": 1.5,
"temperature": 1,
"top_k": 20,
"top_p": 0.95
}