Instructions to use xiapk7/AQuilt_Eval_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xiapk7/AQuilt_Eval_lora with Transformers:

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

pipe = pipeline("text-generation", model="xiapk7/AQuilt_Eval_lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("xiapk7/AQuilt_Eval_lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xiapk7/AQuilt_Eval_lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xiapk7/AQuilt_Eval_lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xiapk7/AQuilt_Eval_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xiapk7/AQuilt_Eval_lora

SGLang

How to use xiapk7/AQuilt_Eval_lora 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 "xiapk7/AQuilt_Eval_lora" \
    --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": "xiapk7/AQuilt_Eval_lora",
		"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 "xiapk7/AQuilt_Eval_lora" \
        --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": "xiapk7/AQuilt_Eval_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xiapk7/AQuilt_Eval_lora with Docker Model Runner:
```
docker model run hf.co/xiapk7/AQuilt_Eval_lora
```

Improve model card: Add paper link, metadata, and enhanced description

by nielsr HF Staff - opened Jul 25, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+32

-3

nielsr

Jul 25, 2025

This PR enhances the model card for the AQuilt LoRA adapter by adding:

The paper link: AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs.
Essential metadata: pipeline_tag: text-generation for better discoverability and library_name: transformers to indicate compatibility with the Hugging Face Transformers library.
A more comprehensive description of the model based on the paper's abstract, explaining the purpose of AQuilt and this LoRA adapter.
A section for citing the associated paper.

These updates aim to improve the model's visibility, context, and usability on the Hugging Face Hub.

Improve model card: Add paper link, metadata, and enhanced description090947f5

xiapk7

Owner Jul 26, 2025

Thank you for your suggestions! We will improve this.

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

Tap or paste here to upload images

Cannot merge

This branch has merge conflicts in the following files:

README.md

· Sign up or log in to comment