Instructions to use bigatuna/Qwen3-1.7B-Sushi-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bigatuna/Qwen3-1.7B-Sushi-Coder with Transformers:

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

pipe = pipeline("text-generation", model="bigatuna/Qwen3-1.7B-Sushi-Coder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bigatuna/Qwen3-1.7B-Sushi-Coder")
model = AutoModelForCausalLM.from_pretrained("bigatuna/Qwen3-1.7B-Sushi-Coder")
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 bigatuna/Qwen3-1.7B-Sushi-Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bigatuna/Qwen3-1.7B-Sushi-Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bigatuna/Qwen3-1.7B-Sushi-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bigatuna/Qwen3-1.7B-Sushi-Coder

SGLang

How to use bigatuna/Qwen3-1.7B-Sushi-Coder 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 "bigatuna/Qwen3-1.7B-Sushi-Coder" \
    --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": "bigatuna/Qwen3-1.7B-Sushi-Coder",
		"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 "bigatuna/Qwen3-1.7B-Sushi-Coder" \
        --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": "bigatuna/Qwen3-1.7B-Sushi-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bigatuna/Qwen3-1.7B-Sushi-Coder with Docker Model Runner:
```
docker model run hf.co/bigatuna/Qwen3-1.7B-Sushi-Coder
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3-1.7B-Sushi-Coder

A fine-tuned Qwen3-1.7B model optimized for code generation and competitive programming.

Model Details

Base Model: Qwen/Qwen3-1.7B
Fine-tuning Method: SFT with LoRA (merged)
Training Steps: 1000
Context Length: 2048

Training

This model was fine-tuned using:

LoRA (r=8, alpha=16) on attention and MLP layers
Liger Kernel for memory efficiency
Packing with FlashAttention-2
Cosine learning rate schedule (2e-5 peak)

Datasets

ericholam/codeforces-sft-dataset-beta - 1408 competitive programming examples
TeichAI/claude-4.5-opus-high-reasoning-250x - High-quality reasoning examples

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "bigatuna/Qwen3-1.7B-Sushi-Coder",
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained("bigatuna/Qwen3-1.7B-Sushi-Coder")

messages = [
    {"role": "user", "content": "Write a Python function to solve the two-sum problem."}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.6, top_p=0.95, top_k=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Sampling Parameters

For best results with Qwen3 models:

Temperature: 0.6-0.7
Top-p: 0.95
Top-k: 20
Do not use greedy decoding (temp=0 causes repetitions)

License

Apache 2.0

Downloads last month: 238

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for bigatuna/Qwen3-1.7B-Sushi-Coder

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Finetuned

(786)

this model

Quantizations

2 models

bigatuna
/

Qwen3-1.7B-Sushi-Coder