mradermacher/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct-GGUF

Same weights, converted vs ytz20/GAD-GPT-5-Chat-Llama-3.2-3B-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: lm_head 0/1, MLP 0/84, Norms 0/57, Attention 0/112, Embeddings 0/1

On the Hub · Downloads on Model Pulse