numen-tech's picture
Add weights
b5c2707
metadata
language:
  - en
license: llama3.1
base_model: NousResearch/Hermes-3-Llama-3.1-8B
base_model_relation: quantized
library_name: mlc-llm
pipeline_tag: text-generation

4-bit OmniQuant quantized version of FuseChat-Llama-3.1-8B-Instruct for inference with the Private LLM app.