nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct-GGUF

Same weights, converted vs nassimjp/MiniCPM5-2B-SFT-Pashto-Instruct. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/85, MLP 0/126, Attention 0/168

On the Hub · Downloads on Model Pulse