Instructions to use guangyangnlp/Qwen3-1.7B-SFT-science-1e-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use guangyangnlp/Qwen3-1.7B-SFT-science-1e-5 with Transformers:

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

pipe = pipeline("text-generation", model="guangyangnlp/Qwen3-1.7B-SFT-science-1e-5")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("guangyangnlp/Qwen3-1.7B-SFT-science-1e-5")
model = AutoModelForMultimodalLM.from_pretrained("guangyangnlp/Qwen3-1.7B-SFT-science-1e-5")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use guangyangnlp/Qwen3-1.7B-SFT-science-1e-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "guangyangnlp/Qwen3-1.7B-SFT-science-1e-5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "guangyangnlp/Qwen3-1.7B-SFT-science-1e-5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/guangyangnlp/Qwen3-1.7B-SFT-science-1e-5

SGLang

How to use guangyangnlp/Qwen3-1.7B-SFT-science-1e-5 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 "guangyangnlp/Qwen3-1.7B-SFT-science-1e-5" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "guangyangnlp/Qwen3-1.7B-SFT-science-1e-5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "guangyangnlp/Qwen3-1.7B-SFT-science-1e-5" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "guangyangnlp/Qwen3-1.7B-SFT-science-1e-5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use guangyangnlp/Qwen3-1.7B-SFT-science-1e-5 with Docker Model Runner:
```
docker model run hf.co/guangyangnlp/Qwen3-1.7B-SFT-science-1e-5
```

Qwen3-1.7B-SFT-science-1e-5 / all_results.json

guangyangnlp

Upload folder using huggingface_hub

9dd7cc0 verified 4 months ago

Raw

History Blame Contribute Delete

351 Bytes

	{
	"epoch": 3.0,
	"eval_loss": 0.7602248191833496,
	"eval_runtime": 138.9352,
	"eval_samples_per_second": 37.37,
	"eval_steps_per_second": 9.342,
	"total_flos": 4.1917370482093916e+18,
	"train_loss": 0.07527349776537244,
	"train_runtime": 3319.5738,
	"train_samples_per_second": 89.138,
	"train_steps_per_second": 0.697
	}