GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
TIGER-Lab
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
TIGER-Lab
Model Tree
Qwen/Qwen2.5-Coder-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen2.5-Coder-7B-Instructmidtraining/configs/fim_midtrain.yaml on TIGER-Lab/FIM-Midtraining-400K (as-run copy: FIM_Midtrain_7B.yaml) → intermediate checkpoint released as TIGER-Lab/FIM-Mid-7Bposttraining/r2egym/ (as-run copy: FIM_Posttrain_7B.yaml)Means over three evaluation seeds, identical harness for both arms (paper Table 1):
| Setting | SWE-Bench-Verified | SWE-Bench-Lite |
|---|---|---|
| Qwen2.5-Coder-7B-Instruct + R2E-Gym (reproduced) | 15.00 | 11.33 |
| FIM-7B (+ FIM mid-training) | 17.80 | 15.00 |
| Δ | +2.80 | +3.67 |
FIM-7B 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.
bash
CUDA_VISIBLE_DEVICES=0 \VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 \python -m vllm.entrypoints.openai.api_server \--model TIGER-Lab/FIM-7B \--served-model-name FIM-7B \--host 127.0.0.1 \--port 8400 \--tensor-parallel-size 1 \--max-model-len 65536 \--hf-overrides '{"max_position_embeddings": 65536}' \--enable-prefix-caching \--gpu-memory-utilization 0.9 \> vllm_fim7b.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
From an upstream, unmodified R2E-Gym checkout (Docker required):
bash
export OPENAI_API_KEY=EMPTYexport LLM_BASE_URL="http://127.0.0.1:8400/v1"uv run python src/r2egym/agenthub/run/edit.py runagent_multiple \--dataset "R2E-Gym/SWE-Bench-Verified" \--split "test" \--start_idx 0 \--k 500 \--traj_dir "./traj" \--exp_name "FIM-7B_swebench_verified_r1" \--llm_name "openai/FIM-7B" \--scaffold "r2egym" \--backend "docker" \--use_fn_calling False \--temperature 0 \--max_steps 40 \--max_steps_absolute 100 \--max_workers 6 \--max_reward_calc_time 1200 \--max_tokens 65536 \--use_existing True
For SWE-Bench Lite, use --dataset "R2E-Gym/SWE-Bench-Lite" --k 300.
Convert the trajectories to a submission and score with the official harness — evaluation/swebench/score.sh. The reported number is resolved_instances / total_instances.
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 arXiv:2607.12463},year={2026}}