mradermacher/Babel-9B-Chat-GGUF
Same weights, converted vs Tower-Babel/Babel-9B-Chat. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/238, lm_head 0/1
Same weights, converted vs Tower-Babel/Babel-9B-Chat. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/69, MLP 0/102, Attention 0/238, lm_head 0/1