tinyopsec/llama3.2-1b-CoT-GGUF
Same weights, converted vs harshwardhanjadhav/llama3.2-1b-CoT. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64
Same weights, converted vs harshwardhanjadhav/llama3.2-1b-CoT. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64