upload intellifold_v2.py

.gitattributes

@@ -35,4 +35,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 protein_id_groups.json filter=lfs diff=lfs merge=lfs -text
 unique_protein_sequences.fasta filter=lfs diff=lfs merge=lfs -text
-pdb_seqres_2022_09_28.fasta filter=lfs diff=lfs merge=lfs -text

README.md

@@ -5,7 +5,6 @@ tags:
 - chemistry
 - biomolecular-structure-prediction
 - IntelliFold
-library_name: intellifold
 ---
 
 ![IntelliFold Cover](https://raw.githubusercontent.com/IntelliGen-AI/IntelliFold/main/assets/intellifold-cover.png)
@@ -19,27 +18,12 @@ library_name: intellifold
 
 <div align="center" style="margin: 20px 0;">
   <span style="margin: 0 10px;">⚡ <a href="https://server.intfold.com">IntelliFold Server</a></span>
-  &bull; <span style="margin: 0 10px;">📄 <a href="https://raw.githubusercontent.com/IntelliGen-AI/IntelliFold/main//Intellifold_v2_release_note.pdf">IntelliFold 2 Release Note</a></span> &bull; <span style="margin: 0 10px;">📄 <a href="https://arxiv.org/abs/2507.02025">IntelliFold Technical Report</a></span>
-
+  &bull; <span style="margin: 0 10px;">📄 <a href="https://arxiv.org/abs/2507.02025">Technical Report</a></span>
 </div>
 
 
 ![IntelliFold Model](https://raw.githubusercontent.com/IntelliGen-AI/IntelliFold/main/assets/Intellifold-Model-Arc.png)
 
-## 🎉 New Model Release
-
- - **2026-02-07**: We are excited to present [[IntelliFold 2]](assets/Intellifold_v2_release_note.pdf). This version represents a
-major architectural update and is one of the first open-source models to outperform AlphaFold3 on
-Foldbench.  
-
-
-## 📊 Benchmarking
-To comprehensively evaluate the performance of IntelliFold 2, we conducted a rigorous evaluation on [FoldBench](https://github.com/BEAM-Labs/FoldBench). We compared IntelliFold against several leading methods, including [Boltz-1,2](https://github.com/jwohlwend/boltz), [Chai-1](https://github.com/chaidiscovery/chai-lab), [Protenix](https://github.com/bytedance/Protenix) and [Alphafold3](https://github.com/google-deepmind/alphafold3).
-
-For more details on the benchmarking process and results, please refer to our release note [IntelliFold 2 Release Note](https://raw.githubusercontent.com/IntelliGen-AI/IntelliFold/main/assets/Intellifold_v2_release_note.pdf) and [IntelliFold Technical Report](https://arxiv.org/abs/2507.02025).
-
-![Benchmark Metrics](https://raw.githubusercontent.com/IntelliGen-AI/IntelliFold/main/assets/Intellifold_v2_performance.png)
-
 
 ## 🚀 Quick Start
 
@@ -65,11 +49,6 @@ To more complete installation instructions and usage, please refer to the [Insta
    intellifold predict your_input.yaml --out_dir ./results
    ```
 
-    IntelliFold v2-Flash will be used by default, you can also use IntelliFold v2 by specifying the model name:
-    ```bash
-    intellifold predict your_input.yaml --out_dir ./results --model v2
-    ```
-
 3. **Check Results**: Find predicted structures and confidence scores in the output directory, you can also check the section of **output format** in [output documentation](https://github.com/IntelliGen-AI/IntelliFold/blob/main/docs/input_yaml_format.md#output-format).
 
 4. **Optional Optimization**: Enable [custom kernels](https://github.com/IntelliGen-AI/IntelliFold/blob/main/docs/kernels.md) for faster inference and reduced memory usage
@@ -77,6 +56,13 @@ To more complete installation instructions and usage, please refer to the [Insta
 For comprehensive usage instructions and examples, refer to the [Usage Guide](https://github.com/IntelliGen-AI/IntelliFold/blob/main/docs/usage.md).
 
 
+## 📊 Benchmarking
+To comprehensively evaluate the performance of To quickly get started with IntelliFold, you can use the following commands:
+, we conducted a rigorous evaluation on [FoldBench](https://github.com/BEAM-Labs/FoldBench). We compared IntelliFold against several leading methods, including [Boltz-1,2](https://github.com/jwohlwend/boltz), [Chai-1](https://github.com/chaidiscovery/chai-lab), [Protenix](https://github.com/bytedance/Protenix) and [Alphafold3](https://github.com/google-deepmind/alphafold3).
+
+For more details on the benchmarking process and results, please refer to our [Technical Report](https://arxiv.org/abs/2507.02025).
+
+![Benchmark Metrics](https://raw.githubusercontent.com/IntelliGen-AI/IntelliFold/main/assets/intellifold_metrics.png)
 
 
 ## 🌐 IntelliFold Server
@@ -91,14 +77,6 @@ For comprehensive usage instructions and examples, refer to the [Usage Guide](ht
 If you use IntelliFold in your research, please cite our paper:
 
 ```
-@techreport{qiao2026intellifold,
-      title={{IntelliFold 2: Surpassing AlphaFold 3 via Architectural Refinement and Structural Consistency}},
-      author={Lifeng Qiao and He Yan and Gary Liu and Gaoxing Guo and Siqi Sun},
-      year={2026},
-      institution={IntelliGen-AI},
-      type={Release Note},
-      url={https://raw.githubusercontent.com/IntelliGen-AI/IntelliFold/main/assets/Intellifold_v2_release_note.pdf}
-}
 @misc{theintfoldteam2025intfoldcontrollablefoundationmodel,
       title={IntFold: A Controllable Foundation Model for General and Specialized Biomolecular Structure Prediction}, 
       author={The IntFold Team and Leon Qiao and Wayne Bai and He Yan and Gary Liu and Nova Xi and Xiang Zhang},

ccd_v2.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8766edb6a88e01461a123e8a4e2d5e33846821b808444737cd82e441998801f8
-size 413033419

intellifold_v2.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ee1c03344a94c8d3408f9579b3869f791701b7945e23255331d44fb7cc41aaa
-size 3401386544

pdb_seqres_2022_09_28.fasta

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1b3bc853322c32f2eea818065b8f569a18d25a52326a8d2c2c3de85752e55fe1
-size 232899463