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

Libraries

How to use PracticalWork/Qwen3-1.7B-tuned with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B")
model = PeftModel.from_pretrained(base_model, "PracticalWork/Qwen3-1.7B-tuned")

Transformers

How to use PracticalWork/Qwen3-1.7B-tuned with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PracticalWork/Qwen3-1.7B-tuned", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PracticalWork/Qwen3-1.7B-tuned with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PracticalWork/Qwen3-1.7B-tuned

SGLang

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

Docker Model Runner
How to use PracticalWork/Qwen3-1.7B-tuned with Docker Model Runner:
```
docker model run hf.co/PracticalWork/Qwen3-1.7B-tuned
```

Qwen3-1.7B-tuned

This model is a fine-tuned version of Qwen/Qwen3-1.7B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.6231
Perplexity: 5.0689

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.003
train_batch_size: 12
eval_batch_size: 12
seed: 42
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: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Perplexity
No log	0	0	6.3047	547.1235
No log	0.6011	333	1.8454	6.3306
1.9738	1.2022	666	1.7511	5.7610
1.9738	1.8032	999	1.6936	5.4388
1.7084	2.4043	1332	1.6532	5.2239
1.7084	3	1664	1.6231	5.0689

Framework versions

PEFT 0.16.0
Transformers 4.54.1
Pytorch 2.7.1+cu128
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: -

Model tree for PracticalWork/Qwen3-1.7B-tuned

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Adapter

(521)

this model

Collection including PracticalWork/Qwen3-1.7B-tuned

Tuned

Collection

Soft-prompted models • 4 items • Updated Oct 15, 2025