We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
我想要评测MuSiQue数据集中的musique_ans_v1.0_dev.jsonl这个文件该如何将其转换为项目需要的格式呢 是不是先要运行prepare_retriever.sh然后部署vllm最后在运行run_evalutation.sh
在运行prepare_retriever.sh的时候我调整成下面的参数 减小了 dense_config.faiss_config.batch_size和 dense_config.batch_size 用两张4090还是爆显存该怎么调整呢 DEVICE_ID='[4,5]' ENCODER_PATH='/Model/bge-large-en-v1.5' data_path='data/musique_ans_v1.0_dev.jsonl'
python -m flexrag.entrypoints.prepare_index retriever_type=dense corpus_path=[$data_path] saving_fields=[id,question,answer,paragraphs,answer_aliases] text_process_pipeline.processor_type=[length_filter] text_process_pipeline.length_filter_config.max_chars=4096 text_process_pipeline.length_filter_config.min_chars=10 text_process_fields=[paragraphs] dense_config.database_path=test dense_config.encode_fields=[paragraphs] dense_config.passage_encoder_config.encoder_type=hf dense_config.passage_encoder_config.hf_config.model_path=$ENCODER_PATH dense_config.passage_encoder_config.hf_config.prompt='query: ' dense_config.passage_encoder_config.hf_config.normalize=True dense_config.passage_encoder_config.hf_config.device_id=$DEVICE_ID dense_config.index_type=faiss dense_config.faiss_config.batch_size=4896 dense_config.faiss_config.log_interval=100000 dense_config.batch_size=4896 dense_config.log_interval=100000
The text was updated successfully, but these errors were encountered:
No branches or pull requests
我想要评测MuSiQue数据集中的musique_ans_v1.0_dev.jsonl这个文件该如何将其转换为项目需要的格式呢
是不是先要运行prepare_retriever.sh然后部署vllm最后在运行run_evalutation.sh
在运行prepare_retriever.sh的时候我调整成下面的参数
减小了 dense_config.faiss_config.batch_size和 dense_config.batch_size
用两张4090还是爆显存该怎么调整呢
DEVICE_ID='[4,5]'
ENCODER_PATH='/Model/bge-large-en-v1.5'
data_path='data/musique_ans_v1.0_dev.jsonl'
python -m flexrag.entrypoints.prepare_index
retriever_type=dense
corpus_path=[$data_path]
saving_fields=[id,question,answer,paragraphs,answer_aliases]
text_process_pipeline.processor_type=[length_filter]
text_process_pipeline.length_filter_config.max_chars=4096
text_process_pipeline.length_filter_config.min_chars=10
text_process_fields=[paragraphs]
dense_config.database_path=test
dense_config.encode_fields=[paragraphs]
dense_config.passage_encoder_config.encoder_type=hf
dense_config.passage_encoder_config.hf_config.model_path=$ENCODER_PATH
dense_config.passage_encoder_config.hf_config.prompt='query: '
dense_config.passage_encoder_config.hf_config.normalize=True
dense_config.passage_encoder_config.hf_config.device_id=$DEVICE_ID
dense_config.index_type=faiss
dense_config.faiss_config.batch_size=4896
dense_config.faiss_config.log_interval=100000
dense_config.batch_size=4896
dense_config.log_interval=100000
The text was updated successfully, but these errors were encountered: