Modelpublic

meteorain/Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_qwen3-cot-traces

sourceHugging Faceupdated 5mo agoView on Hugging Face

0likes5downloads

3 commits on main

dc6c88b5mo ago

Strip orphan weight_scale/weight_zero_point tensors so the BF16 checkpoint loads cleanly in vLLM (no quantization_config in config.json).

meteorain

0bcae295mo ago

Upload Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_qwen3-cot-traces

meteorain

08dc7da5mo ago

initial commit

meteorain