Instructions to use Mrigendra100/XpathGenerator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mrigendra100/XpathGenerator with Transformers:

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

pipe = pipeline("text-generation", model="Mrigendra100/XpathGenerator")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mrigendra100/XpathGenerator")
model = AutoModelForCausalLM.from_pretrained("Mrigendra100/XpathGenerator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mrigendra100/XpathGenerator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mrigendra100/XpathGenerator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mrigendra100/XpathGenerator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mrigendra100/XpathGenerator

SGLang

How to use Mrigendra100/XpathGenerator 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 "Mrigendra100/XpathGenerator" \
    --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": "Mrigendra100/XpathGenerator",
		"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 "Mrigendra100/XpathGenerator" \
        --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": "Mrigendra100/XpathGenerator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mrigendra100/XpathGenerator with Docker Model Runner:
```
docker model run hf.co/Mrigendra100/XpathGenerator
```

You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card for Mrigendra100/XpathGenerator

Model Details

Model Name: Mrigendra100/XpathGenerator
Base Model: EleutherAI/gpt-neo-1.3B
Task: Text generation (specifically for generating XPath expressions from HTML)

Library

Transformers: This model uses the Hugging Face transformers library for handling pre-trained models and performing inference.

Usage

To use this model, you can leverage the transformers library from Hugging Face. Below is an example of how to load and use the model for inference:

from transformers import pipeline

# Load the model and tokenizer
generator = pipeline("text-generation", model="Mrigendra100/XpathGenerator")

# Generate XPath from input HTML
input_html = '<button class="btn relative btn-primary shrink-0"><div class="flex justify-center">Get Plus</div></button>'
generated_xpath = generator(input_html, max_length=50)

print("Generated XPath:", generated_xpath)

Downloads last month: -

Safetensors

Model size

1B params

Tensor type

F32

Model tree for Mrigendra100/XpathGenerator

Base model

EleutherAI/gpt-neo-1.3B

Finetuned

(39)

this model