afrideva/llama-160m-GGUF
Same weights, converted vs JackFram/llama-160m. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/48
Same weights, converted vs JackFram/llama-160m. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/48