gemma-4-31B-it-SFT_OCR-INT8
INT8 quantization of lokeshe09/gemma-4-31B-it-SFT_OCR, produced with llm-compressor.
Vision encoder, lm_head, embeddings, and norm layers are kept in original precision.
- Downloads last month
- 9
Model tree for lokeshe09/gemma-4-31B-it-SFT_OCR-INT8
Base model
google/gemma-4-31B Finetuned
google/gemma-4-31B-it Finetuned
unsloth/gemma-4-31B-it Finetuned
lokeshe09/gemma-4-31B-it-SFT_OCR