James Kelly
cloned most of ctmatch into this spaces repo... it will have to handle the data too, we'll see. using ctmatch requirements.txt
8155451
| #ctproc uncoment if doing data prep on raw ct documents | |
| #https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.4.0/en_core_sci_md-0.4.0.tar.gz uncomment if using ctproc | |
| #pyserini==0.12.0 uncomment if using ctproc with indexes (not recommended) | |
| #git+https://github.com/semajyllek/transformers.git@add-biogpt-sequenceclassifier | |
| #sacremoses uncomment if using biogpt | |
| sentence-transformers | |
| huggingface_hub | |
| scikit-learn | |
| transformers | |
| onnxruntime | |
| nn_pruning | |
| optimum | |
| onnx | |
| matplotlib | |
| accelerate | |
| datasets | |
| evaluate | |
| pandas | |
| openai | |
| lxml | |
| gradio |