mradermacher/MathSmith-HC-Qwen3-8B-Qwen2_5-32B-ShortCoT-GGUF

Same weights, converted vs Jasaxion/MathSmith-HC-Qwen3-8B-Qwen2_5-32B-ShortCoT. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144, lm_head 0/1

On the Hub · Downloads on Model Pulse