hadad/ qwen3-4bd:BF16

126 1 week ago

Qwen3 fine-tuned using an ultra massive distilled dataset derived from a range of powerful AI models, including Kimi K2.5, Qwen 3.5, Claude Opus 4.6, Claude Opus 4.5, Gemini 3 Pro, Claude Haiku 4.5, GPT 5.2, Gemini 3.1 Pro, GLM 4.7, GLM 5 .......

tools thinking
... /
params
882459668cff · 130B
{
"min_p": 0,
"repeat_penalty": 1,
"stop": [
"<|im_start|>",
"<|im_end|>"
],
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95
}