DevQuasar/tiiuae.Falcon-H1-1.5B-Base-GGUF

Same weights, converted vs tiiuae/Falcon-H1-1.5B-Base. Same weights stored in another dtype (BF16 → F16/F32), plus 72 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/25, MLP 0/72, Attention 0/96

On the Hub · Downloads on Model Pulse