navispace/Qwen3.8-27B-W8A16-GPTQ

Update README.md

Update README.md

Update README.md

Update README.md

add vocab.json (faltou no upload original)

add tokenizer_config.json (faltou no upload original)

add video_preprocessor_config.json (faltou no upload original)

add preprocessor_config.json (faltou no upload original)

add model.safetensors.index.json (faltou no upload original)

W8A16 GPTQ (RTN, no calibration) wB: model card

W8A16 GPTQ (RTN, no calibration) wB: model-00007.safetensors

W8A16 GPTQ (RTN, no calibration) wA: model-00008.safetensors

W8A16 GPTQ (RTN, no calibration) wA: model-00005.safetensors

W8A16 GPTQ (RTN, no calibration) wB: model-00006.safetensors

W8A16 GPTQ (RTN, no calibration) wA: model-00003.safetensors

W8A16 GPTQ (RTN, no calibration) wB: model-00004.safetensors

W8A16 GPTQ (RTN, no calibration) wA: model-00001.safetensors

W8A16 GPTQ (RTN, no calibration) wB: model-00002.safetensors

Delete .tmp-castest.bin with huggingface_hub

Upload .tmp-castest.bin with huggingface_hub

resume-test 1

xet test

W8A16 GPTQ (RTN, no calibration): merges.txt

W8A16 GPTQ (RTN, no calibration): generation_config.json

W8A16 GPTQ (RTN, no calibration): config.json

W8A16 GPTQ (RTN, no calibration): chat_template.jinja

initial commit