Instructions to use Steven10429/qwen2.5_7b_instruct_finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Steven10429/qwen2.5_7b_instruct_finetune with Transformers:

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

pipe = pipeline("text-generation", model="Steven10429/qwen2.5_7b_instruct_finetune")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Steven10429/qwen2.5_7b_instruct_finetune", device_map="auto")

PEFT
How to use Steven10429/qwen2.5_7b_instruct_finetune with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Steven10429/qwen2.5_7b_instruct_finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Steven10429/qwen2.5_7b_instruct_finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Steven10429/qwen2.5_7b_instruct_finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Steven10429/qwen2.5_7b_instruct_finetune

SGLang

How to use Steven10429/qwen2.5_7b_instruct_finetune 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 "Steven10429/qwen2.5_7b_instruct_finetune" \
    --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": "Steven10429/qwen2.5_7b_instruct_finetune",
		"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 "Steven10429/qwen2.5_7b_instruct_finetune" \
        --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": "Steven10429/qwen2.5_7b_instruct_finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Steven10429/qwen2.5_7b_instruct_finetune with Docker Model Runner:
```
docker model run hf.co/Steven10429/qwen2.5_7b_instruct_finetune
```

Improve language tag

by lbourdois - opened Apr 28, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+61

-47

lbourdois

Apr 28, 2025

Hi! As the model is multilingual, this is a PR to add other languages than English to the language tag to improve the referencing. Note that 29 languages are announced in the README, but only 13 are explicitly listed. I was therefore only able to add these 13 languages.

Improve language tag345f13b3

Steven10429

Owner Apr 28, 2025

Hi, thank you for the PR.

Currently, there is no listed language tag because the README was auto-generated by AutoTrain.
I am only fine-tuning the model with a Chinese dataset.
Even though adding a language tag is a nice idea for clarity,
since the model is mainly in Chinese, I prefer to leave it without extra language tags for now.

Thanks again for your effort, but I won't accept this change.

Steven10429 changed pull request status to closed Apr 28, 2025

lbourdois

Apr 28, 2025

Indeed, my loop referencing all the Qwen-2.5 models to be tagged didn't take into account the case of finetuning on other specific language than the ones in the original model
Sorry for the inconvenience

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment