picur/picur-120M-instruct-gguf
Same weights, converted vs picur/picur-120M-instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/2, other 0/72, MLP 0/144, Norms 0/120, Attention 0/48
Same weights, converted vs picur/picur-120M-instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/2, other 0/72, MLP 0/144, Norms 0/120, Attention 0/48