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

README.md

@@ -4,31 +4,49 @@ library_name: transformers
 pipeline_tag: text-generation
 base_model:
 - Qwen/Qwen3-8B
+datasets:
+- TIGER-Lab/FIM-Midtraining-400K
+- SWE-Lego/SWE-Lego-Synthetic-Data
 tags:
 - code
 - software-engineering
 - agent
 ---
 
-# FIM-8B Inference on SWE-Bench Verified
+# FIM-8B
 
-This guide describes how to run the **FIM-8B** checkpoint on SWE-Bench Verified (and Lite). Unlike FIM-7B and FIM-14B (R2E-Gym scaffold), this model is post-trained on SWE-Lego trajectories and is evaluated with the SWE-Lego setup: OpenHands `CodeActAgent` for inference and the official SWE-bench harness for scoring.
+[📄 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-8B** is the strongest released model of *"Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models"*: `Qwen3-8B`, mid-trained on function-aware FIM data, then post-trained on SWE-Lego agent trajectories. The mid-training stage is the only difference from a standard SWE-Lego reproduction — worth **+3.2 points on SWE-Bench-Verified and +5.4 on SWE-Bench-Lite**. Unlike FIM-7B and FIM-14B (R2E-Gym scaffold), this model is evaluated with the SWE-Lego setup: OpenHands `CodeActAgent` for inference and the official SWE-bench harness for scoring.
 
-Local path: `models/FIM-8B/` (checkpoints are gitignored; do not commit them).
+## Training pipeline
 
-- Base model: `Qwen/Qwen3-8B`
-- FIM mid-training: FIM v2/v3 data
-- Post-training: SFT on SWE-Lego trajectories
+- **Base model**: [`Qwen/Qwen3-8B`](https://huggingface.co/Qwen/Qwen3-8B)
+- **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_8B.yaml`](https://github.com/TIGER-AI-Lab/FIM-Midtraining/blob/main/midtraining/configs/FIM_Midtrain_8B.yaml)) → intermediate checkpoint released as [TIGER-Lab/FIM-Mid-8B](https://huggingface.co/TIGER-Lab/FIM-Mid-8B)
+- **Post-training**: SFT on SWE-Lego trajectories (real + synthetic, `resolved`-filtered, 2 epochs) — [`posttraining/swe_lego/`](https://github.com/TIGER-AI-Lab/FIM-Midtraining/tree/main/posttraining/swe_lego) (as-run copy: [`FIM_Posttrain_8B.yaml`](https://github.com/TIGER-AI-Lab/FIM-Midtraining/blob/main/posttraining/swe_lego/FIM_Posttrain_8B.yaml))
 
+## Results
 
-## 1. Serve the model with vLLM
+Means over three evaluation seeds, identical harness for both arms (paper Table 1):
+
+| Setting | SWE-Bench-Verified | SWE-Bench-Lite |
+|---|---|---|
+| Qwen3-8B + SWE-Lego (reproduced) | 31.80 | 27.30 |
+| **FIM-8B (+ FIM mid-training)** | **35.00** | **32.70** |
+| Δ | +3.20 | +5.40 |
+
+## Evaluate on SWE-Bench Verified
+
+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
+
+The checkpoint ships `max_position_embeddings: 163840` and its own chat template, so no rope or template overrides are needed:
 
 ```bash
 CUDA_VISIBLE_DEVICES=0 \
 python -m vllm.entrypoints.openai.api_server \
-  --model models/FIM-8B \
+  --model TIGER-Lab/FIM-8B \
   --served-model-name FIM-8B \
   --host 127.0.0.1 \
   --port 8400 \
@@ -39,17 +57,15 @@ python -m vllm.entrypoints.openai.api_server \
   > vllm_fim8b.log 2>&1 &
 ```
 
-The checkpoint ships `max_position_embeddings: 163840` and its own chat template, so no rope or template overrides are needed.
-
 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
 
-Inference uses OpenHands 0.53.0. Define the LLM in `config.toml`:
+Inference uses OpenHands 0.53.0 with `CodeActAgent`. Define the LLM in `config.toml`:
 
 ```toml
 [llm.eval_fim]
@@ -83,6 +99,17 @@ poetry run python evaluation/benchmarks/swe_bench/run_infer.py \
 
 For SWE-Bench Lite, use `--dataset princeton-nlp/SWE-bench_Lite`.
 
-## 3. Score with the SWE-bench harness
+### 3. Score with the SWE-bench harness
 
 Convert the OpenHands `output.jsonl` to a predictions file with `evaluation/benchmarks/swe_bench/scripts/eval/convert_oh_output_to_swe_json.py`, then evaluate it with the official SWE-bench harness (`python -m swebench.harness.run_evaluation`). The reported score 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}
+}
+```