左其右

[InternVL2.5](https://huggingface.co/collections/OpenGVLab/internvl25-673e1019b66e2218f68d7c1c) was released a while ago, but it's not yet supported by AutoAWQ. Although they have released an AWQ-quantized model on their Hugging Face page, it's formatted for TensorFlow, which...

[New Model] Support LLaMA 4 family

2

### 🚀 The feature, motivation and pitch The Llama 4 models are auto-regressive language models that use a mixture-of-experts (MoE) architecture and incorporate early fusion for native multimodality. https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct ###...