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, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("vanta-research/wraith-coder-7b")
model = AutoModelForMultimodalLM.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 / model_info.json

Tyler Williams

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

cc49567 7 months ago

raw

history blame

1.32 kB

	{
	"model_name": "wraith-coder-7b",
	"base_model": "Qwen/Qwen2.5-Coder-7B-Instruct",
	"version": "1.0.0",
	"release_date": "2025-11-19",

	"architecture": {
	"type": "CausalLM",
	"parameters": "7.6B",
	"layers": 28,
	"hidden_size": 3584,
	"attention_heads": 28,
	"kv_heads": 4,
	"context_length": 32768,
	"vocab_size": 152064
	},

	"training": {
	"method": "LoRA Fine-tuning",
	"iterations": 3,
	"total_examples": 14244,
	"lora_rank": 16,
	"lora_alpha": 32,
	"learning_rate": 5e-5,
	"epochs_per_iteration": 2,
	"optimizer": "adamw_8bit"
	},

	"performance": {
	"conciseness_improvement": "62.6%",
	"complexity_analysis_coverage": "60%",
	"base_model_complexity_coverage": "40%",
	"evaluation_questions": 20,
	"correctness_rate": "100%"
	},

	"recommended_parameters": {
	"temperature": 0.7,
	"top_p": 0.9,
	"top_k": 40,
	"repeat_penalty": 1.1,
	"max_tokens": 2048
	},

	"quantization": {
	"supported_formats": ["fp16", "q8_0", "q4_k_m", "q4_0"],
	"recommended": "q4_k_m",
	"model_size_q4_k_m": "4.4GB"
	},

	"license": "Apache-2.0",
	"languages": ["en"],
	"tags": [
	"code-generation",
	"algorithms",
	"systems-programming",
	"complexity-analysis",
	"qwen2.5",
	"fine-tuned"
	]
	}