DevQuasar/ai21labs.AI21-Jamba-Reasoning-3B-GGUF
Same weights, converted vs ai21labs/AI21-Jamba-Reasoning-3B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/84, Norms 0/57, Attention 0/8
Same weights, converted vs ai21labs/AI21-Jamba-Reasoning-3B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 0/84, Norms 0/57, Attention 0/8