tensorblock/CodeLlama-13b-Python-hf-GGUF

Quantization vs codellama/CodeLlama-13b-Python-hf. tensorblock/CodeLlama-13b-Python-hf-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 81 tensors match exactly and 282 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1

On the Hub · Downloads on Model Pulse