Instructions to use TIGER-Lab/FIM-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TIGER-Lab/FIM-14B with Transformers:

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

pipe = pipeline("text-generation", model="TIGER-Lab/FIM-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TIGER-Lab/FIM-14B")
model = AutoModelForCausalLM.from_pretrained("TIGER-Lab/FIM-14B", device_map="auto")
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-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TIGER-Lab/FIM-14B"
# 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-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TIGER-Lab/FIM-14B

SGLang

How to use TIGER-Lab/FIM-14B 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-14B" \
    --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-14B",
		"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-14B" \
        --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-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TIGER-Lab/FIM-14B with Docker Model Runner:
```
docker model run hf.co/TIGER-Lab/FIM-14B
```

lllqaq commited on Jul 14

Commit

e843f12

verified ·

1 Parent(s): 0f37ba8

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -9,7 +9,6 @@ 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
-- Format: bf16 safetensors, 6 shards, ~29.6 GB on disk (~27.6 GiB GPU memory at load)
 ## 1. Serve the model with vLLM

 - 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