Instructions to use JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py with Transformers:

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

pipe = pipeline("text-generation", model="JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py")
model = AutoModelForCausalLM.from_pretrained("JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py

SGLang

How to use JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py 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-Research/OpenCoder-1.5B-Path-Distance-Py" \
    --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-Research/OpenCoder-1.5B-Path-Distance-Py",
		"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-Research/OpenCoder-1.5B-Path-Distance-Py" \
        --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-Research/OpenCoder-1.5B-Path-Distance-Py",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py with Docker Model Runner:
```
docker model run hf.co/JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py
```

Description

This model is derived from OpenCoder-1.5B-Base by applying additional context extension fine-tuning. The repository context is composed using the Path Distance .py composer, more details on which, along with others, can be found in the On Pretraining for Project-Level Code Completion paper (arxiv). Specifically, Section A.1 of the Appendix describes the context composition method, and Table 3 provides a comparison with other composers from the same collection.

We publish this checkpoint to support the reproducibility and accessibility of our research results.

Quickstart

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "JetBrains-Research/OpenCoder-1.5B-Path-Distance-Py"
tokenizer_name = "infly/OpenCoder-1.5B-Base"

model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             device_map="auto",
                                             trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(tokenizer_name, trust_remote_code=True)

inputs = tokenizer("# write a quick sort algorithm", return_tensors="pt")
outputs = model.generate(**inputs.to(model.device), max_new_tokens=256)

result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)