mradermacher/Llama-3.2-3B-Unsloth-TechWriter-LoRA-GGUF

Same weights, converted vs Shankarblr/Llama-3.2-3B-TechWriter-Instruct-Unsloth. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

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

On the Hub · Downloads on Model Pulse