Instructions to use JetBrains/Mellum-4b-sft-python with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JetBrains/Mellum-4b-sft-python with Transformers:

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

pipe = pipeline("text-generation", model="JetBrains/Mellum-4b-sft-python")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JetBrains/Mellum-4b-sft-python")
model = AutoModelForCausalLM.from_pretrained("JetBrains/Mellum-4b-sft-python")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use JetBrains/Mellum-4b-sft-python with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JetBrains/Mellum-4b-sft-python"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JetBrains/Mellum-4b-sft-python",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/JetBrains/Mellum-4b-sft-python

SGLang

How to use JetBrains/Mellum-4b-sft-python 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 "JetBrains/Mellum-4b-sft-python" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JetBrains/Mellum-4b-sft-python",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "JetBrains/Mellum-4b-sft-python" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JetBrains/Mellum-4b-sft-python",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use JetBrains/Mellum-4b-sft-python with Docker Model Runner:
```
docker model run hf.co/JetBrains/Mellum-4b-sft-python
```

topshik commited on Apr 30, 2025

Commit

919a794

verified ·

1 Parent(s): a4eec8e

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -9

README.md CHANGED Viewed

@@ -219,18 +219,23 @@ print("### Prediction")
 print(tokenizer.decode(out[0][input_len:]))
 ```
-## Fill in the middle generation
 ```python
-prefix = """
-def fibonacci(n: int) -> int:
-"""
-suffix = """
-if __name__ == "__main__":
-    print(fibonacci(10))
-"""
-encoded_input = tokenizer(f"<fim_suffix>{suffix}<fim_prefix>{prefix}<fim_middle>", return_tensors='pt', return_token_type_ids=False)
 out = model.generate(
     **encoded_input,
     max_new_tokens=100,

 print(tokenizer.decode(out[0][input_len:]))
 ```
+## Fill in the middle with additional files as context generation
 ```python
+example = """<filename>utils.py
+def multiply(x, y):
+    return x * y
+<filename>config.py
+DEBUG = True
+MAX_VALUE = 100
+<filename>example.py
+<fim_suffix>
+# Test the function
+result = calculate_sum(5, 10)
+print(result)<fim_prefix>def calculate_sum(a, b):
+<fim_middle>"""
+encoded_input = tokenizer(example, return_tensors='pt', return_token_type_ids=False)
 out = model.generate(
     **encoded_input,
     max_new_tokens=100,