76 1 week ago

A lightweight distilled Qwen2.5-based local model tuned for fast inference, general-purpose chat, and efficient on-device use. Good for everyday assistance, concise reasoning, and low-footprint deployments.

tools
134fa3d20087 · 111B
{
"min_p": 0.1,
"stop": [
"<|im_end|>",
"<|endoftext|>",
"Anthropic",
"Claude"
],
"temperature": 1.5
}