numen-tech/EVA-LLaMA-3.33-70B-v0.1-w4a16g128sym
0
4-bit OmniQuant quantized version of EVA-LLaMA-3.33-70B-v0.1 for inference with the Private LLM app.
4-bit OmniQuant quantized version of EVA-LLaMA-3.33-70B-v0.1 for inference with the Private LLM app.