wuxing0105 commited on
Commit
05362b3
·
verified ·
1 Parent(s): 5327b21

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -7
README.md CHANGED
@@ -36,7 +36,7 @@ This Hugging Face package is designed for immediate use after download, rapid lo
36
  | Scenario | Description |
37
  | :---: | :--- |
38
  | Complex structure prediction | Takes a Protenix JSON file and locally generated MSA features as input and outputs predicted structures in CIF format and confidence scores in JSON format. |
39
- | Full Hugging Face package validation | Uses the included `config/`, `models/`, `scripts/`, `examples/`, and `weight/` directories to run preflight checks and inference directly. |
40
  | Fine-tuning pipeline validation | Starts the fine-tuning workflow using the included weights and `ft_datasets/finetune_subset.txt`. |
41
  | Training pipeline setup | Supports single-GPU training once the complete Protenix dataset is provided. |
42
 
@@ -87,8 +87,9 @@ pip install onescience[bio] -i http://mirrors.onescience.ai:3141/pypi/simple/ -
87
  ### 2. Download the Model Package and Dataset
88
 
89
  ```bash
90
- hf download --model OneScience-Group/protenix --local-dir ./protenix
91
- hf download --model OneScience-Group/protenix_dataset --local-dir ./protenix_dataset
 
92
  ```
93
 
94
  ### Model Weights
@@ -106,14 +107,14 @@ python scripts/preflight.py --strict-weights --strict-imports
106
  If the full dataset is already prepared:
107
 
108
  ```bash
109
- export DATA_ROOT_DIR=../bio_protenix_dataset
110
  python scripts/preflight.py --strict-weights --strict-imports --strict-data
111
  ```
112
 
113
  ### 4. Run Inference
114
 
115
  ```bash
116
- export DATA_ROOT_DIR=../bio_protenix_dataset
117
  bash scripts/inference_unified_demo.sh
118
  ```
119
 
@@ -128,14 +129,14 @@ output_unified/7r6r/seed_101/predictions/
128
  Training:
129
 
130
  ```bash
131
- export DATA_ROOT_DIR=../bio_protenix_dataset
132
  bash scripts/train_demo.sh
133
  ```
134
 
135
  Fine-tuning:
136
 
137
  ```bash
138
- export DATA_ROOT_DIR=../bio_protenix_dataset
139
  bash scripts/finetune_demo.sh
140
  ```
141
 
 
36
  | Scenario | Description |
37
  | :---: | :--- |
38
  | Complex structure prediction | Takes a Protenix JSON file and locally generated MSA features as input and outputs predicted structures in CIF format and confidence scores in JSON format. |
39
+ | Full Hugging Face package validation | Uses the included `config/`, `models/`, `scripts/`, `examples/`, and `weights/` directories to run preflight checks and inference directly. |
40
  | Fine-tuning pipeline validation | Starts the fine-tuning workflow using the included weights and `ft_datasets/finetune_subset.txt`. |
41
  | Training pipeline setup | Supports single-GPU training once the complete Protenix dataset is provided. |
42
 
 
87
  ### 2. Download the Model Package and Dataset
88
 
89
  ```bash
90
+ hf download OneScience-Group/protenix --local-dir ./protenix
91
+ hf download OneScience-Group/protenix_dataset --repo-type dataset --local-dir ./protenix_dataset
92
+ cd protenix
93
  ```
94
 
95
  ### Model Weights
 
107
  If the full dataset is already prepared:
108
 
109
  ```bash
110
+ export DATA_ROOT_DIR=../protenix_dataset
111
  python scripts/preflight.py --strict-weights --strict-imports --strict-data
112
  ```
113
 
114
  ### 4. Run Inference
115
 
116
  ```bash
117
+ export DATA_ROOT_DIR=../protenix_dataset
118
  bash scripts/inference_unified_demo.sh
119
  ```
120
 
 
129
  Training:
130
 
131
  ```bash
132
+ export DATA_ROOT_DIR=../protenix_dataset
133
  bash scripts/train_demo.sh
134
  ```
135
 
136
  Fine-tuning:
137
 
138
  ```bash
139
+ export DATA_ROOT_DIR=../protenix_dataset
140
  bash scripts/finetune_demo.sh
141
  ```
142