JahongirB/uzocr-8b-GGUF

Quantization (fewer layers) vs JahongirB/uzocr-8b. JahongirB/uzocr-8b-GGUF matches part of JahongirB/uzocr-8b (399 of its 750 tensors; the rest of JahongirB/uzocr-8b has no counterpart). On the shared part: JahongirB/uzocr-8b-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 254 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144

On the Hub · Downloads on Model Pulse