mradermacher/TRACE-Mix-Qwen2.5-3B-Instruct-GGUF

Same weights, converted vs XiaoyuWen/TRACE-Mix-Qwen2.5-3B-Instruct. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Norms 0/73, MLP 0/108, Attention 0/252, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse