mradermacher/EXAGIRL-2.4B-Instruct-GGUF

Same weights, converted vs huggingface-KREW/EXAGIRL-2.4B-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Attention 0/120, Norms 0/61, MLP 0/90, Embeddings 0/1

On the Hub · Downloads on Model Pulse