Instructions to use 17Lab/qwen3b-full-sft-s13 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 17Lab/qwen3b-full-sft-s13 with Transformers:

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

pipe = pipeline("text-generation", model="17Lab/qwen3b-full-sft-s13")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("17Lab/qwen3b-full-sft-s13")
model = AutoModelForCausalLM.from_pretrained("17Lab/qwen3b-full-sft-s13", device_map="auto")
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 17Lab/qwen3b-full-sft-s13 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "17Lab/qwen3b-full-sft-s13"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "17Lab/qwen3b-full-sft-s13",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/17Lab/qwen3b-full-sft-s13

SGLang

How to use 17Lab/qwen3b-full-sft-s13 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 "17Lab/qwen3b-full-sft-s13" \
    --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": "17Lab/qwen3b-full-sft-s13",
		"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 "17Lab/qwen3b-full-sft-s13" \
        --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": "17Lab/qwen3b-full-sft-s13",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 17Lab/qwen3b-full-sft-s13 with Docker Model Runner:
```
docker model run hf.co/17Lab/qwen3b-full-sft-s13
```

qwen3b-full-sft-s13 / README.md

Yiqi-Liu

Upload folder using huggingface_hub

4223df5 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

1.71 kB

	---
	library_name: transformers
	license: other
	base_model: Qwen/Qwen2.5-3B
	tags:
	- llama-factory
	- full
	- generated_from_trainer
	model-index:
	- name: qwen3b_full_sft_8gpu_s13
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# qwen3b_full_sft_8gpu_s13

	This model is a fine-tuned version of [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B) on the assimilation_strict_json_v2 dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.0001

	## Model description

	More information needed

	## Intended uses & limitations

	More information needed

	## Training and evaluation data

	More information needed

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 3e-05
	- train_batch_size: 8
	- eval_batch_size: 2
	- seed: 13
	- distributed_type: multi-GPU
	- num_devices: 8
	- gradient_accumulation_steps: 2
	- total_train_batch_size: 128
	- total_eval_batch_size: 16
	- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_steps: 0.05
	- num_epochs: 3

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:-----:\|:----:\|:---------------:\|
	\| 0.0128 \| 1.32 \| 50 \| 0.0003 \|
	\| 0.0001 \| 2.64 \| 100 \| 0.0001 \|
	\| 0.0001 \| 3.0 \| 114 \| 0.0001 \|


	### Framework versions

	- Transformers 5.6.0
	- Pytorch 2.7.0+cu128
	- Datasets 4.0.0
	- Tokenizers 0.22.2