mradermacher/MedSSR-Qwen3-8B-Base-GGUF
Same weights, converted vs tdlhl/MedSSR-Qwen3-8B-Base. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: MLP 0/108, Norms 0/145, Attention 0/144, Embeddings 0/1, lm_head 0/1
Same weights, converted vs tdlhl/MedSSR-Qwen3-8B-Base. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: MLP 0/108, Norms 0/145, Attention 0/144, Embeddings 0/1, lm_head 0/1