bartowski/hkust-nlp_dsv2-lite-coder_codeio_pp-GGUF

Quantization vs hkust-nlp/dsv2-lite-coder_codeio_pp. bartowski/hkust-nlp_dsv2-lite-coder_codeio_pp-GGUF is a GGUF quantization (Q8_0) of the same weights: 108 tensors match exactly and 191 within quantization error.

Tensors changed: Embeddings 0/1, Attention 0/108, Norms 0/82, MLP 0/107, lm_head 0/1

On the Hub · Downloads on Model Pulse