TIGER-Lab / FIM-14B

FIM-14B Inference on SWE-Bench Verified

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.

Model

Local path: models/FIM-14B/ (checkpoints are gitignored; do not commit them).

• Base model: Qwen/Qwen2.5-Coder-14B-Instruct
• FIM mid-training: train/FIM_Midtrain_14B.yaml
• Post-training: SFT on R2E-Gym agent trajectories

1. Serve the model with vLLM

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 \
  --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):

curl -s http://127.0.0.1:8400/v1/models

2. Run the agent on SWE-Bench Verified

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