mradermacher/AI21-Jamba-Reasoning-3B-heretic-GGUF
Same weights, converted vs K0D3IN/AI21-Jamba-Reasoning-3B-heretic. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/8
Same weights, converted vs K0D3IN/AI21-Jamba-Reasoning-3B-heretic. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/8