mradermacher/Falcon-H1-Tiny-Multilingual-100M-Instruct-GGUF

Same weights, converted vs tiiuae/Falcon-H1-Tiny-Multilingual-100M-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 24 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96

On the Hub · Downloads on Model Pulse