Instructions to use vanta-research/wraith-coder-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vanta-research/wraith-coder-7b with Transformers:

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

pipe = pipeline("text-generation", model="vanta-research/wraith-coder-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vanta-research/wraith-coder-7b")
model = AutoModelForCausalLM.from_pretrained("vanta-research/wraith-coder-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 vanta-research/wraith-coder-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/vanta-research/wraith-coder-7b

SGLang

How to use vanta-research/wraith-coder-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 "vanta-research/wraith-coder-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": "vanta-research/wraith-coder-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 "vanta-research/wraith-coder-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": "vanta-research/wraith-coder-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vanta-research/wraith-coder-7b with Docker Model Runner:
```
docker model run hf.co/vanta-research/wraith-coder-7b
```

wraith-coder-7b

Commit History

Update README.md

54c4374
verified

unmodeled-tyler commited on Jan 20

Update README.md

e3bff17
verified

unmodeled-tyler commited on Nov 24, 2025

Update README.md

b93577a
verified

unmodeled-tyler commited on Nov 23, 2025

Update README.md

54d994d
verified

unmodeled-tyler commited on Nov 19, 2025

Add tokenizer files with LFS tracking

308063f

Tyler Williams commited on Nov 19, 2025

Track large tokenizer files with Git LFS

9ea5eeb

Tyler Williams commited on Nov 19, 2025

Merge initial HuggingFace commit with local model files

98efef1

Tyler Williams commited on Nov 19, 2025

Initial commit: Wraith Coder 7B - Concise code assistant via iterative fine-tuning

cc49567

Tyler Williams commited on Nov 19, 2025

initial commit

eff2b28

unmodeled-tyler commited on Nov 19, 2025

Commit History

Update README.md 54c4374 verified

Update README.md e3bff17 verified

Update README.md b93577a verified

Update README.md 54d994d verified

Add tokenizer files with LFS tracking 308063f

Track large tokenizer files with Git LFS 9ea5eeb

Merge initial HuggingFace commit with local model files 98efef1

Initial commit: Wraith Coder 7B - Concise code assistant via iterative fine-tuning cc49567

initial commit eff2b28

Update README.md

54c4374
verified

Update README.md

e3bff17
verified

Update README.md

b93577a
verified

Update README.md

54d994d
verified

Add tokenizer files with LFS tracking

308063f

Track large tokenizer files with Git LFS

9ea5eeb

Merge initial HuggingFace commit with local model files

98efef1

Initial commit: Wraith Coder 7B - Concise code assistant via iterative fine-tuning

cc49567

initial commit

eff2b28