tensorblock/Octopus-v2-GGUF
Quantization vs NexaAI/Octopus-v2. tensorblock/Octopus-v2-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 37 tensors match exactly and 127 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/37, MLP 0/54, Attention 0/72