mradermacher/Llama3.2-TaiPhone-3B-Instruct-v0.2-GGUF

Same weights, converted vs aqweteddy/Llama3.2-TaiPhone-3B-Instruct-v0.2. 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