Xddchvh / tokenizer_config.json

Upload INT4 quantized Gemma‑3‑1B‑IT QAT with bfloat16 compute, extreme shrinkage (100% weight prune, only weights saved), and extensive unconventional modifications including GPTQ/AWQ flags (bfloat16 compute)

b3b3372 verified 8 months ago

raw

history contribute delete

1.16 MB

File too large to display, you can check the raw version instead.