llmfan46/AI21-Jamba2-Mini-Ultra-Uncensored-Heretic-GGUF

Same weights, converted vs llmfan46/AI21-Jamba2-Mini-Ultra-Uncensored-Heretic. Same weights stored in another dtype (BF16 → BF16/F32), plus 48 new tensors.

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

On the Hub · Downloads on Model Pulse