Instructions to use TIGER-Lab/FIM-Mid-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TIGER-Lab/FIM-Mid-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="TIGER-Lab/FIM-Mid-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TIGER-Lab/FIM-Mid-7B")
model = AutoModelForCausalLM.from_pretrained("TIGER-Lab/FIM-Mid-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TIGER-Lab/FIM-Mid-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TIGER-Lab/FIM-Mid-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/FIM-Mid-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TIGER-Lab/FIM-Mid-7B

SGLang

How to use TIGER-Lab/FIM-Mid-7B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "TIGER-Lab/FIM-Mid-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/FIM-Mid-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "TIGER-Lab/FIM-Mid-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/FIM-Mid-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TIGER-Lab/FIM-Mid-7B with Docker Model Runner:
```
docker model run hf.co/TIGER-Lab/FIM-Mid-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

FIM-Mid-7B

📄 Paper · 💻 GitHub · 🤗 Dataset · 🤗 Collection

FIM-Mid-7B is the mid-trained checkpoint of the FIM 7B pipeline: Qwen2.5-Coder-7B-Instruct after function-aware FIM mid-training, before agent post-training. Post-training this checkpoint on R2E-Gym agent trajectories produces TIGER-Lab/FIM-7B.

It is released for reproducibility and further post-training. The paper deliberately never scores mid-training-only checkpoints — a FIM-only model has degraded instruction-following and cannot be compared fairly against instruction-tuned baselines; every reported gain is one that survives post-training.

Training

Base model: Qwen/Qwen2.5-Coder-7B-Instruct
FIM mid-training: midtraining/configs/fim_midtrain.yaml on TIGER-Lab/FIM-Midtraining-400K — AdamW, lr 1.0e-5, cosine schedule, warmup ratio 0.1, weight decay 0.05, one epoch, sequence length 32768, bf16 (as-run copy: FIM_Midtrain_7B.yaml)
Post-training: none — see TIGER-Lab/FIM-7B for the post-trained agent model

Serve with vLLM

A standard Qwen2.5 checkpoint; no overrides needed at its native 32768 context:

CUDA_VISIBLE_DEVICES=0 \
python -m vllm.entrypoints.openai.api_server \
  --model TIGER-Lab/FIM-Mid-7B \
  --served-model-name FIM-Mid-7B \
  --host 127.0.0.1 \
  --port 8400 \
  --tensor-parallel-size 1 \
  --max-model-len 32768 \
  --gpu-memory-utilization 0.9 \
  > vllm_fim_mid7b.log 2>&1 &

Post-training

To reproduce FIM-7B, run R2E-Gym trajectory SFT from this checkpoint — the exact config is posttraining/r2egym/FIM_Posttrain_7B.yaml (LLaMA-Factory, full fine-tuning, lr 1.0e-5, 2 epochs, cutoff 32768), which already points at this repo id. See posttraining/r2egym/ for the walkthrough.

Citation

@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}
}