DevQuasar/tiiuae.Falcon-H1-3B-Instruct-GGUF

Same weights, converted vs tiiuae/Falcon-H1-3B-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 96 new tensors.

Tensors changed: Embeddings 0/1, MLP 0/96, Norms 0/33, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse