finance-Llama3-8B

git clone https://github.com/microsoft/LMOps
   cd LMOps/adaptllm
   pip install -r requirements.txt

# Select the domain from ['biomedicine', 'finance']
   DOMAIN='finance'
  
   # Specify any Huggingface LM name (Not applicable to models requiring specific prompt templates)
   MODEL='instruction-pretrain/finance-Llama3-8B'
  
   # Model parallelization:
   # - Set MODEL_PARALLEL=False if the model fits on a single GPU. 
   #   We observe that LMs smaller than 10B always meet this requirement.
   # - Set MODEL_PARALLEL=True if the model is too large and encounters OOM on a single GPU.
   MODEL_PARALLEL=False
  
   # Choose the number of GPUs from [1, 2, 4, 8]
   N_GPU=1
  
   # Whether to add a BOS token at the beginning of the prompt input:
   # - Set to False for AdaptLLM.
   # - Set to True for instruction-pretrain models.
   # If unsure, we recommend setting it to False, as this is suitable for most LMs.
   add_bos_token=True

   # Run the evaluation script
   bash scripts/inference.sh ${DOMAIN} ${MODEL} ${add_bos_token} ${MODEL_PARALLEL} ${N_GPU}