Upload README.md with huggingface_hub

README.md

@@ -22,6 +22,8 @@ This repository contains the trained PACMT model files and taxonomy resources. T
 https://github.com/luanbei/PACMT
 ```
 
+Use the current scripts from the GitHub repository's `script/` directory. The three prediction scripts require `pacmt_retrained_common.py` in that same directory.
+
 ## Model description
 
 PACMT uses a two-stage serial workflow:
@@ -48,6 +50,7 @@ PACMT/
 │   ├── bert_padding.py
 │   └── flash_attn_triton.py
 ├── binary_model/
+│   ├── config.json
 │   ├── pytorch_model.bin
 │   ├── head_config.json
 │   ├── tokenizer.json
@@ -126,7 +129,7 @@ models/
 The complete two-stage PACMT workflow first performs binary viral screening and then applies hierarchical taxonomic classification to sequences predicted as viral.
 
 ```bash
-python scripts/predict_binary_hierarchy.py \
+python script/predict_bina_hiera.py \
   --backbone_dir models/backbone \
   --binary_ckpt_dir models/binary_model \
   --hierarchy_ckpt_dir models/hierarchy_model \
@@ -154,7 +157,7 @@ For FASTA input, replace the CSV input arguments with:
 ## Binary viral screening only
 
 ```bash
-python scripts/predict_binary.py \
+python script/predict_binary.py \
   --backbone_dir models/backbone \
   --ckpt_dir models/binary_model \
   --input_csv examples/example.csv \
@@ -173,7 +176,7 @@ python scripts/predict_binary.py \
 ## Hierarchical classification only
 
 ```bash
-python scripts/predict_hierarchy.py \
+python script/predict_hierarchy.py \
   --backbone_dir models/backbone \
   --ckpt_dir models/hierarchy_model \
   --mapping_csv models/taxonomy/label_taxonomy_mapping.csv \