Instructions to use Bifrost-AI/Qwen3-Bifrost-SOL-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bifrost-AI/Qwen3-Bifrost-SOL-4B with Transformers:

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

pipe = pipeline("text-generation", model="Bifrost-AI/Qwen3-Bifrost-SOL-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Bifrost-AI/Qwen3-Bifrost-SOL-4B")
model = AutoModelForCausalLM.from_pretrained("Bifrost-AI/Qwen3-Bifrost-SOL-4B")
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 Bifrost-AI/Qwen3-Bifrost-SOL-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Bifrost-AI/Qwen3-Bifrost-SOL-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Bifrost-AI/Qwen3-Bifrost-SOL-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Bifrost-AI/Qwen3-Bifrost-SOL-4B

SGLang

How to use Bifrost-AI/Qwen3-Bifrost-SOL-4B 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 "Bifrost-AI/Qwen3-Bifrost-SOL-4B" \
    --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": "Bifrost-AI/Qwen3-Bifrost-SOL-4B",
		"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 "Bifrost-AI/Qwen3-Bifrost-SOL-4B" \
        --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": "Bifrost-AI/Qwen3-Bifrost-SOL-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Bifrost-AI/Qwen3-Bifrost-SOL-4B with Docker Model Runner:
```
docker model run hf.co/Bifrost-AI/Qwen3-Bifrost-SOL-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3 Bifrost SOL 4B

This fine-tuned variant of the Qwen 4B model was supervised fine-tuned on blockchain-specific datasets(Bifrost-AI/Solana-Vanguard-Challenge), optimized for downstream tasks in blockchain coding and smart contract development on the Solana ecosystem.

The Solana Vanguard Challenge dataset, comprising 1,000 diverse and in-depth questions, offers full-spectrum coverage of the Solana ecosystem. It spans fundamental blockchain concepts, advanced on-chain programming in Rust and the Anchor framework, client-side integration in TypeScript, detailed security strategies, and performance as well as regulatory considerations.

Qwen3 Bifrost SOL 4B is in active development with additional fine-tuning sessions, & benchmark statistics coming soon!

Training Session:

Time: 11 hours & 22 minutes
GPU: NVIDIA GeForce RTX 3090
Batches: 1000
Context-Size: 2098
Batch-size: 1
Learning-rate: 2e-5
Training-loss: 1.06
Eval-loss: 0.81

Dataset Composition

Total Questions: 1,000
Languages Covered:
- Rust: On-chain smart contract development, security best practices, advanced state management, CPIs, PDAs, and more.
- TypeScript: Client-side integration using @solana/web3.js, wallet adapters, Metaplex for NFT protocols, dynamic transaction composition, and front-end dApp development.
Planned Extensions:
- C# (Solnet): To be integrated later for .NET ecosystem coverage.