unsloth/Trinity-Large-Preview-GGUF

Same weights, converted vs arcee-ai/Trinity-Large-Preview. Same weights stored in another dtype (BF16 → BF16/F32), plus 216 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/361, MLP 0/234, Attention 0/300

On the Hub · Downloads on Model Pulse