Instructions to use microsoft/NextCoder-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/NextCoder-7B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/NextCoder-7B")
model = AutoModelForCausalLM.from_pretrained("microsoft/NextCoder-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/NextCoder-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/NextCoder-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": "microsoft/NextCoder-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/NextCoder-7B

SGLang

How to use microsoft/NextCoder-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 "microsoft/NextCoder-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": "microsoft/NextCoder-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 "microsoft/NextCoder-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": "microsoft/NextCoder-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/NextCoder-7B with Docker Model Runner:
```
docker model run hf.co/microsoft/NextCoder-7B
```

Updated link

by adityakanade - opened Jun 12, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-1

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -119,7 +119,7 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 *Comparison of base QwenCoder-2.5 models of different sizes and their SELEKT-enhanced versions across three code editing benchmarks.*
-**Detailed evaluation results are reported in this [📑 paper](https://arxiv.org/abs/2503.03656).**
 ## Responsible AI Use
 The base models (from the QwenCoder-2.5 family) are suspectible to malicious prompts and may generate or execute harmful code. Our finetuning does not enhance or impede such behaviors. The users should use the models and their outputs responsibly and with caution. Model outputs should be subjected to additional analysis, including manual inspection, and sandboxing before execution.

 *Comparison of base QwenCoder-2.5 models of different sizes and their SELEKT-enhanced versions across three code editing benchmarks.*
+**Detailed evaluation results are reported in this [📑 paper](https://www.microsoft.com/en-us/research/publication/nextcoder-robust-adaptation-of-code-lms-to-diverse-code-edits/).**
 ## Responsible AI Use
 The base models (from the QwenCoder-2.5 family) are suspectible to malicious prompts and may generate or execute harmful code. Our finetuning does not enhance or impede such behaviors. The users should use the models and their outputs responsibly and with caution. Model outputs should be subjected to additional analysis, including manual inspection, and sandboxing before execution.