Instructions to use jajajou/qwen2.5-7b-instruct-vn-law-tax with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jajajou/qwen2.5-7b-instruct-vn-law-tax with Transformers:

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

pipe = pipeline("text-generation", model="jajajou/qwen2.5-7b-instruct-vn-law-tax")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jajajou/qwen2.5-7b-instruct-vn-law-tax")
model = AutoModelForCausalLM.from_pretrained("jajajou/qwen2.5-7b-instruct-vn-law-tax")
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

vLLM

How to use jajajou/qwen2.5-7b-instruct-vn-law-tax with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jajajou/qwen2.5-7b-instruct-vn-law-tax"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jajajou/qwen2.5-7b-instruct-vn-law-tax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jajajou/qwen2.5-7b-instruct-vn-law-tax

SGLang

How to use jajajou/qwen2.5-7b-instruct-vn-law-tax 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 "jajajou/qwen2.5-7b-instruct-vn-law-tax" \
    --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": "jajajou/qwen2.5-7b-instruct-vn-law-tax",
		"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 "jajajou/qwen2.5-7b-instruct-vn-law-tax" \
        --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": "jajajou/qwen2.5-7b-instruct-vn-law-tax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use jajajou/qwen2.5-7b-instruct-vn-law-tax with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jajajou/qwen2.5-7b-instruct-vn-law-tax to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for jajajou/qwen2.5-7b-instruct-vn-law-tax to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jajajou/qwen2.5-7b-instruct-vn-law-tax to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="jajajou/qwen2.5-7b-instruct-vn-law-tax",
    max_seq_length=2048,
)

Docker Model Runner
How to use jajajou/qwen2.5-7b-instruct-vn-law-tax with Docker Model Runner:
```
docker model run hf.co/jajajou/qwen2.5-7b-instruct-vn-law-tax
```

Vietnamese Legal Assistant - Qwen2.5 7B

Đây là model trợ lý pháp lý tiếng Việt được fine-tune từ Qwen2.5-7B-Instruct.

Mô tả

Model này được huấn luyện để:

Trả lời các câu hỏi pháp lý bằng tiếng Việt
Đưa ra lời khuyên dựa trên luật pháp Việt Nam
Hỗ trợ hiểu biết về các quy định pháp luật

Lưu ý

Model này chỉ mang tính chất tham khảo
Không thay thế cho lời khuyên của luật sư chuyên nghiệp
Luôn tham khảo ý kiến chuyên gia khi cần

Uploaded finetuned model

Developed by: jajajou
License: apache-2.0
Finetuned from model : unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for jajajou/qwen2.5-7b-instruct-vn-law-tax

Merges

1 model