bartowski/ai21labs_AI21-Jamba2-Mini-GGUF

Same weights, converted vs ai21labs/AI21-Jamba2-Mini. Same weights stored in another dtype (BF16 → BF16/F32), plus 48 new tensors.

Tensors changed: Embeddings 0/1, MLP 0/64, Norms 0/65, Attention 0/16, lm_head 0/1

On the Hub · Downloads on Model Pulse