Update model card: official GitHub/dataset links, unified training configs, results, citation

README.md

@@ -4,32 +4,57 @@ library_name: transformers
 pipeline_tag: text-generation
 base_model:
 - Qwen/Qwen2.5-Coder-14B-Instruct
+datasets:
+- TIGER-Lab/FIM-Midtraining-400K
+- R2E-Gym/R2EGym-SFT-Trajectories
 tags:
 - code
 - software-engineering
 - agent
 ---
 
-# FIM-14B Inference on SWE-Bench Verified
+# FIM-14B
 
-This guide describes how to run the **FIM-14B** checkpoint on SWE-Bench Verified (and Lite) with the R2E-Gym agent scaffold in this repository.
+[📄 Paper (PDF)](https://github.com/TIGER-AI-Lab/FIM-Midtraining/blob/main/paper.pdf) · [💻 GitHub](https://github.com/TIGER-AI-Lab/FIM-Midtraining) · [🤗 Dataset](https://huggingface.co/datasets/TIGER-Lab/FIM-Midtraining-400K) · [🤗 Collection](https://huggingface.co/collections/TIGER-Lab/fim-midtraining)
 
-## Model
+**FIM-14B** is the 14B coding-agent model of *"Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models"*: `Qwen2.5-Coder-14B-Instruct`, mid-trained on function-aware FIM data, then post-trained on R2E-Gym agent trajectories with the upstream recipe unmodified. The mid-training stage is the only difference from a standard R2E-Gym reproduction — worth **+3.0 points on SWE-Bench-Verified and +4.0 on SWE-Bench-Lite**, while also recovering most of the general-capability erosion that agentic post-training inflicts (LiveCodeBench +11.1, τ-bench +3.9, BFCL +2.4 over the post-training-only arm).
 
-Local path: `models/FIM-14B/` (checkpoints are gitignored; do not commit them).
+## Training pipeline
 
-- Base model: `Qwen/Qwen2.5-Coder-14B-Instruct`
-- FIM mid-training: `train/FIM_Midtrain_14B.yaml`
-- Post-training: SFT on R2E-Gym agent trajectories
+- **Base model**: [`Qwen/Qwen2.5-Coder-14B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct)
+- **FIM mid-training**: [`midtraining/configs/fim_midtrain.yaml`](https://github.com/TIGER-AI-Lab/FIM-Midtraining/blob/main/midtraining/configs/fim_midtrain.yaml) on [TIGER-Lab/FIM-Midtraining-400K](https://huggingface.co/datasets/TIGER-Lab/FIM-Midtraining-400K) (as-run copy: [`FIM_Midtrain_14B.yaml`](https://github.com/TIGER-AI-Lab/FIM-Midtraining/blob/main/midtraining/configs/FIM_Midtrain_14B.yaml)) → intermediate checkpoint released as [TIGER-Lab/FIM-Mid-14B](https://huggingface.co/TIGER-Lab/FIM-Mid-14B)
+- **Post-training**: SFT on R2E-Gym agent trajectories — [`posttraining/r2egym/`](https://github.com/TIGER-AI-Lab/FIM-Midtraining/tree/main/posttraining/r2egym) (as-run copy: [`FIM_Posttrain_14B.yaml`](https://github.com/TIGER-AI-Lab/FIM-Midtraining/blob/main/posttraining/r2egym/FIM_Posttrain_14B.yaml))
 
+## Results
 
-## 1. Serve the model with vLLM
+Means over three evaluation seeds, identical harness for both arms (paper Tables 1–2):
+
+| Setting | SWE-Bench-Verified | SWE-Bench-Lite |
+|---|---|---|
+| Qwen2.5-Coder-14B-Instruct + R2E-Gym (reproduced) | 26.20 | 18.00 |
+| **FIM-14B (+ FIM mid-training)** | **29.20** | **22.00** |
+| Δ | +3.00 | +4.00 |
+
+Capability preservation at 14B (six benchmarks outside SWE-Bench):
+
+| Setting | LiveCode | OJBench | FSB-EN | Terminal | τ-bench | BFCL | Avg |
+|---|---|---|---|---|---|---|---|
+| + R2E-Gym only | 24.10 | 2.80 | 47.72 | 2.41 | 3.40 | 15.80 | 16.04 |
+| **FIM-14B** | **35.20** | **4.74** | **48.25** | **3.66** | **7.30** | **18.20** | **19.56** |
+
+Reproduction guides for all six: [`evaluation/`](https://github.com/TIGER-AI-Lab/FIM-Midtraining/tree/main/evaluation).
+
+## Evaluate on SWE-Bench Verified
+
+FIM-14B is evaluated with the **R2E-Gym agent scaffold** (fixed by its post-training pipeline). The complete pinned walkthrough lives at [`evaluation/swebench/released_checkpoints.md`](https://github.com/TIGER-AI-Lab/FIM-Midtraining/blob/main/evaluation/swebench/released_checkpoints.md).
+
+### 1. Serve the model with vLLM
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 \
 VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 \
-.venv-vllm/bin/python -m vllm.entrypoints.openai.api_server \
-  --model models/FIM-14B \
+python -m vllm.entrypoints.openai.api_server \
+  --model TIGER-Lab/FIM-14B \
   --served-model-name FIM-14B \
   --host 127.0.0.1 \
   --port 8400 \
@@ -41,14 +66,15 @@ VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 \
   > vllm_fim14b.log 2>&1 &
 ```
 
-
 Wait until the server is up (model load takes ~1 minute):
 
 ```bash
 curl -s http://127.0.0.1:8400/v1/models
 ```
 
-## 2. Run the agent on SWE-Bench Verified
+### 2. Run the agent on SWE-Bench Verified
+
+From an upstream, unmodified [R2E-Gym](https://github.com/R2E-Gym/R2E-Gym) checkout (Docker required):
 
 ```bash
 export OPENAI_API_KEY=EMPTY
@@ -74,3 +100,19 @@ uv run python src/r2egym/agenthub/run/edit.py runagent_multiple \
   --use_existing True
 ```
 
+For SWE-Bench Lite, use `--dataset "R2E-Gym/SWE-Bench-Lite" --k 300`.
+
+### 3. Score with the official SWE-bench harness
+
+Convert the trajectories to a submission and score with the official harness — [`evaluation/swebench/score.sh`](https://github.com/TIGER-AI-Lab/FIM-Midtraining/blob/main/evaluation/swebench/score.sh). The reported number is `resolved_instances / total_instances`.
+
+## Citation
+
+```bibtex
+@article{wang2026fim,
+  title={Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models},
+  author={Wang, Yubo and Liang, Jiarong and Zhang, Yuxuan and Liu, Xuye and Wei, Cong and Zhang, Yuyu and Nie, Ping and Chen, Wenhu},
+  journal={arXiv preprint},
+  year={2026}
+}
+```