mradermacher/Fijik-3b-Instruct-GGUF
Same weights, converted vs Pinkstackorg/Fijik1-3b-instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/168, Attention 0/392
Same weights, converted vs Pinkstackorg/Fijik1-3b-instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/168, Attention 0/392