TIGER-Lab

FIM-14B

Deploy Dedicated

README

License: apache-2.0

Training pipeline

Base model: Qwen/Qwen2.5-Coder-14B-Instruct
FIM mid-training: midtraining/configs/fim_midtrain.yaml on TIGER-Lab/FIM-Midtraining-400K (as-run copy: FIM_Midtrain_14B.yaml) → intermediate checkpoint released as TIGER-Lab/FIM-Mid-14B
Post-training: SFT on R2E-Gym agent trajectories — posttraining/r2egym/ (as-run copy: FIM_Posttrain_14B.yaml)

Results

Means over three evaluation seeds, identical harness for both arms (paper Tables 1–2):

Table with columns: Setting, SWE-Bench-Verified, SWE-Bench-Lite
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):

Table with columns: Setting, LiveCode, OJBench, FSB-EN, Terminal, τ-bench, BFCL, Avg
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

Reproduction guides for all six: 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.

1. Serve the model with vLLM

bash
CUDA_VISIBLE_DEVICES=0 \
VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 \
python -m vllm.entrypoints.openai.api_server \
  --model TIGER-Lab/FIM-14B \
  --served-model-name FIM-14B \
  --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_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

From an upstream, unmodified R2E-Gym checkout (Docker required):

bash
export OPENAI_API_KEY=EMPTY
export 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-14B_swebench_verified_r1" \
  --llm_name "openai/FIM-14B" \
  --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.

3. Score with the official SWE-bench harness

Convert the trajectories to a submission and score with the official harness — 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 arXiv:2607.12463},
  year={2026}
}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

TIGER-Lab

Model Tree

Base

Qwen/Qwen2.5-Coder-14B-Instruct

Fine-tuned

this model

Input Modalities

Text

Output Modalities