Modelpublic

Intel/Qwen2-0.5B-Instruct-int4-sym-AutoRound

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

1likes27kdownloads

Model Card

This model is an int4 model with group_size 128 and symmetric quantization of Qwen/Qwen2-0.5B-Instruct generated by intel/auto-round algorithm.

⚠️ Important: This model is used for internal testing with VLLM. Please do not delete or modify without approval.