8 10 months ago

A THOX configuration and distribution of Alibaba Cloud's Qwen3 235B MoE, the largest model in the MagStack cluster family, published for local inference and MeshStack deployments. Apache-2.0.

a73abadd02cb ยท 138B
{
"num_ctx": 131072,
"repeat_penalty": 1.1,
"stop": [
"<|im_start|>",
"<|im_end|>"
],
"temperature": 0.7,
"top_k": 40,
"top_p": 0.9
}