mradermacher/nemotron-3-8b-chat-4k-sft-hf-GGUF
Same weights, converted vs mgoin/nemotron-3-8b-chat-4k-sft-hf. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/130, MLP 0/64, Attention 0/128
Same weights, converted vs mgoin/nemotron-3-8b-chat-4k-sft-hf. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/130, MLP 0/64, Attention 0/128