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

Libraries

How to use 17Lab/qwen3b-lora-sft-s13 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B")
model = PeftModel.from_pretrained(base_model, "17Lab/qwen3b-lora-sft-s13")

Transformers

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

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("17Lab/qwen3b-lora-sft-s13", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

qwen3b-lora-sft-s13 / README.md

Yiqi-Liu

Upload folder using huggingface_hub

fd099bb verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

1.75 kB

metadata

library_name: peft
license: other
base_model: Qwen/Qwen2.5-3B
tags:
  - base_model:adapter:Qwen/Qwen2.5-3B
  - llama-factory
  - lora
  - transformers
pipeline_tag: text-generation
model-index:
  - name: qwen3b_lora_sft_8gpu_s13
    results: []

qwen3b_lora_sft_8gpu_s13

This model is a fine-tuned version of Qwen/Qwen2.5-3B on the assimilation_strict_json_v2 dataset. It achieves the following results on the evaluation set:

Loss: 0.1501

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: 0.00015
train_batch_size: 16
eval_batch_size: 4
seed: 13
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 128
total_eval_batch_size: 32
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
0.1844	1.3158	50	0.1810
0.1501	2.6316	100	0.1501
0.1501	3.0	114	0.1501

Framework versions

PEFT 0.18.1
Transformers 5.6.0
Pytorch 2.7.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2