--- language: - en license: llama3.1 base_model: cognitivecomputations/Dolphin3.0-Llama3.1-8B base_model_relation: quantized library_name: mlc-llm pipeline_tag: text-generation --- 3-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [Dolphin3.0-Llama3.1-8B](https://huggingface.co/cognitivecomputations/Dolphin3.0-Llama3.1-8B) for inference with [Private LLM](https://privatellm.app).