philbert440/Qwen3.8-27B-Uncensored-Aggressive-W4A16-AWQ

Add files using upload-large-folder tool

Add stock-vLLM starter above the 1Cat-vLLM V100 serve command

Add vLLM serve command (1Cat-vLLM 2x V100 + stock Ampere)

Fix tokenizer: drop leftover truncation block, restore upstream tokenizer.json/tokenizer_config.json (fixes vision >1024 tokens; see discussion #3)

Upload README.md with huggingface_hub

Upload folder using huggingface_hub

initial commit