varadsrivastava/lm-playschool-qwen3.5-2b-sft-dpo-vllm
072
Upload README.md with huggingface_hub
vLLM-compatible: composite qwen3_5 config + base vision weights grafted in
initial commit
Upload README.md with huggingface_hub
vLLM-compatible: composite qwen3_5 config + base vision weights grafted in
initial commit