afrideva/smol_llama-220M-GQA-GGUF
Same weights, converted vs BEE-spoke-data/smol_llama-220M-GQA. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/21, MLP 0/30, Attention 0/40
Same weights, converted vs BEE-spoke-data/smol_llama-220M-GQA. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/21, MLP 0/30, Attention 0/40