wulezhi/qwen3.8-27b-buddhist

re-upload to correct path: gguf/Q6/qwen3.8-27b-Buddhist-16bit.Q6_K.gguf

remove wrongly nested path: gguf/Q6/qwen3.8-27b-Buddhist-16bit.Q6_K.gguf/qwen3.8-27b-Buddhist-16bit.Q6_K.gguf

upload qwen38-int8-w8a8

upload gguf/Q6/qwen3.8-27b-Buddhist-16bit.Q6_K.gguf

upload gguf/Q4

remove wrongly nested path (will re-upload correctly)

probe cleanup

probe: commit endpoint check

upload gguf/Q4/qwen3.8-27b-Buddhist-16bit.Q4_K_M.gguf

upload qwen38-gptq-w4a16

upload qwen38-awq-w4a16

Fix model card: dense arch, dict corpus, quant load per framework

upload qwen38-autoawq-w4a16

remove speedtest artifact

Upload .speedtest.tmp with huggingface_hub

upload qwen38-autoawq-w4a16/config.json

upload qwen38-autoawq-w4a16/chat_template.jinja

upload qwen38-autoawq-w4a16/generation_config.json

add qwen3.8-27b-Buddhist-16bit.BF16-mmproj.gguf

add adapter_model.safetensors

add adapter_config.json

add README.md

initial commit