model_params.cfg

[retriever]
MODEL = BAAI/bge-large-en-v1.5
NORMALIZE = 1
TOP_K = 20
[ranker]
MODEL = BAAI/bge-reranker-base
TOP_K = 3
[reader]
TYPE = NVIDIA
DEDICATED_MODEL = meta-llama/Llama-3.1-8B-Instruct
DEDICATED_ENDPOINT = https://qu2d8m6dmsollhly.us-east-1.aws.endpoints.huggingface.cloud
NVIDIA_MODEL = meta-llama/Meta-Llama-3.1-8B-Instruct
NVIDIA_ENDPOINT = https://huggingface.co/api/integrations/dgx/v1
MAX_TOKENS = 512