numen-tech's picture
Add weights
d4f7adc
metadata
language:
  - en
license: llama3
base_model: TsinghuaC3I/Llama-3.1-8B-UltraMedical
base_model_relation: quantized
library_name: mlc-llm
pipeline_tag: text-generation

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