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 / trainer_log.jsonl

Yiqi-Liu

Upload folder using huggingface_hub

4223df5 verified about 1 month ago

Raw

History Blame Contribute Delete

5.13 kB

	{"current_steps": 5, "total_steps": 114, "loss": 3.1597023010253906, "lr": 1.9999999999999998e-05, "epoch": 0.13333333333333333, "percentage": 4.39, "elapsed_time": "0:00:10", "remaining_time": "0:03:41"}
	{"current_steps": 10, "total_steps": 114, "loss": 0.903958511352539, "lr": 2.9942920471376185e-05, "epoch": 0.26666666666666666, "percentage": 8.77, "elapsed_time": "0:00:15", "remaining_time": "0:02:36"}
	{"current_steps": 15, "total_steps": 114, "loss": 0.33176212310791015, "lr": 2.959567305869736e-05, "epoch": 0.4, "percentage": 13.16, "elapsed_time": "0:00:19", "remaining_time": "0:02:11"}
	{"current_steps": 20, "total_steps": 114, "loss": 0.1942599296569824, "lr": 2.8940212863402334e-05, "epoch": 0.5333333333333333, "percentage": 17.54, "elapsed_time": "0:00:24", "remaining_time": "0:01:56"}
	{"current_steps": 25, "total_steps": 114, "loss": 0.14255876541137696, "lr": 2.7990381056766583e-05, "epoch": 0.6666666666666666, "percentage": 21.93, "elapsed_time": "0:00:29", "remaining_time": "0:01:46"}
	{"current_steps": 30, "total_steps": 114, "loss": 0.1059659481048584, "lr": 2.6766234973793638e-05, "epoch": 0.8, "percentage": 26.32, "elapsed_time": "0:00:34", "remaining_time": "0:01:37"}
	{"current_steps": 35, "total_steps": 114, "loss": 0.06367313861846924, "lr": 2.5293624568031008e-05, "epoch": 0.9333333333333333, "percentage": 30.7, "elapsed_time": "0:00:39", "remaining_time": "0:01:29"}
	{"current_steps": 40, "total_steps": 114, "loss": 0.04107189476490021, "lr": 2.360364654526569e-05, "epoch": 1.0533333333333332, "percentage": 35.09, "elapsed_time": "0:00:44", "remaining_time": "0:01:21"}
	{"current_steps": 45, "total_steps": 114, "loss": 0.025246787071228027, "lr": 2.1731987703006933e-05, "epoch": 1.1866666666666668, "percentage": 39.47, "elapsed_time": "0:00:49", "remaining_time": "0:01:15"}
	{"current_steps": 50, "total_steps": 114, "loss": 0.012763623893260957, "lr": 1.9718171342274207e-05, "epoch": 1.32, "percentage": 43.86, "elapsed_time": "0:00:54", "remaining_time": "0:01:09"}
	{"current_steps": 50, "total_steps": 114, "eval_loss": 0.0002999651478603482, "epoch": 1.32, "percentage": 43.86, "elapsed_time": "0:00:56", "remaining_time": "0:01:12"}
	{"current_steps": 55, "total_steps": 114, "loss": 0.0002823648974299431, "lr": 1.760472266500396e-05, "epoch": 1.4533333333333334, "percentage": 48.25, "elapsed_time": "0:02:35", "remaining_time": "0:02:46"}
	{"current_steps": 60, "total_steps": 114, "loss": 0.00017986295279115438, "lr": 1.543627078114667e-05, "epoch": 1.5866666666666667, "percentage": 52.63, "elapsed_time": "0:02:40", "remaining_time": "0:02:24"}
	{"current_steps": 65, "total_steps": 114, "loss": 0.0001341827679425478, "lr": 1.3258606288121545e-05, "epoch": 1.72, "percentage": 57.02, "elapsed_time": "0:02:45", "remaining_time": "0:02:05"}
	{"current_steps": 70, "total_steps": 114, "loss": 0.00011214115656912326, "lr": 1.1117714323462188e-05, "epoch": 1.8533333333333335, "percentage": 61.4, "elapsed_time": "0:02:51", "remaining_time": "0:01:47"}
	{"current_steps": 75, "total_steps": 114, "loss": 9.917097631841897e-05, "lr": 9.058803509412647e-06, "epoch": 1.9866666666666668, "percentage": 65.79, "elapsed_time": "0:02:56", "remaining_time": "0:01:31"}
	{"current_steps": 80, "total_steps": 114, "loss": 9.251137380488217e-05, "lr": 7.1253512949815995e-06, "epoch": 2.1066666666666665, "percentage": 70.18, "elapsed_time": "0:03:01", "remaining_time": "0:01:17"}
	{"current_steps": 85, "total_steps": 114, "loss": 8.82596941664815e-05, "lr": 5.3581858547019095e-06, "epoch": 2.24, "percentage": 74.56, "elapsed_time": "0:03:06", "remaining_time": "0:01:03"}
	{"current_steps": 90, "total_steps": 114, "loss": 8.51782620884478e-05, "lr": 3.7946239313850626e-06, "epoch": 2.3733333333333335, "percentage": 78.95, "elapsed_time": "0:03:11", "remaining_time": "0:00:51"}
	{"current_steps": 95, "total_steps": 114, "loss": 8.472277550026774e-05, "lr": 2.467682828805956e-06, "epoch": 2.506666666666667, "percentage": 83.33, "elapsed_time": "0:03:17", "remaining_time": "0:00:39"}
	{"current_steps": 100, "total_steps": 114, "loss": 8.298547472804785e-05, "lr": 1.4053831944502509e-06, "epoch": 2.64, "percentage": 87.72, "elapsed_time": "0:03:22", "remaining_time": "0:00:28"}
	{"current_steps": 100, "total_steps": 114, "eval_loss": 8.276944572571665e-05, "epoch": 2.64, "percentage": 87.72, "elapsed_time": "0:03:24", "remaining_time": "0:00:28"}
	{"current_steps": 105, "total_steps": 114, "loss": 8.245615754276514e-05, "lr": 6.301573152676665e-07, "epoch": 2.7733333333333334, "percentage": 92.11, "elapsed_time": "0:05:03", "remaining_time": "0:00:26"}
	{"current_steps": 110, "total_steps": 114, "loss": 8.253837004303932e-05, "lr": 1.5837542128583294e-07, "epoch": 2.9066666666666667, "percentage": 96.49, "elapsed_time": "0:05:08", "remaining_time": "0:00:11"}
	{"current_steps": 114, "total_steps": 114, "eval_loss": 8.275313302874565e-05, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:05:14", "remaining_time": "0:00:00"}
	{"current_steps": 114, "total_steps": 114, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:06:48", "remaining_time": "0:00:00"}