mradermacher/AutoTriton-GGUF
Same weights, converted vs ai9stars/AutoTriton. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/96, Norms 0/65, Attention 0/128, lm_head 0/1
Same weights, converted vs ai9stars/AutoTriton. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/96, Norms 0/65, Attention 0/128, lm_head 0/1