Instructions to use yoonusajward01/triptuner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yoonusajward01/triptuner with Transformers:

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

pipe = pipeline("text-generation", model="yoonusajward01/triptuner")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yoonusajward01/triptuner")
model = AutoModelForCausalLM.from_pretrained("yoonusajward01/triptuner", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yoonusajward01/triptuner with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yoonusajward01/triptuner"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yoonusajward01/triptuner",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/yoonusajward01/triptuner

SGLang

How to use yoonusajward01/triptuner 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 "yoonusajward01/triptuner" \
    --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": "yoonusajward01/triptuner",
		"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 "yoonusajward01/triptuner" \
        --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": "yoonusajward01/triptuner",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use yoonusajward01/triptuner with Docker Model Runner:
```
docker model run hf.co/yoonusajward01/triptuner
```

triptuner / README.md

yoonusajward01

Update README.md

00f257f verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

1.73 kB

	---
	library_name: transformers
	tags:
	- gpt2
	- transformers
	- text-generation
	- adventure
	- travel-itinerary
	- custom-model
	pipeline_tag: text-generation
	---

	# TripTuner: Adventure Travel Itinerary Generator for Central Province, Sri Lanka

	## Overview

	TripTuner is a custom-trained GPT-2 model designed to generate personalized adventure travel itineraries specifically for locations within the Central Province of Sri Lanka. The model is fine-tuned to provide detailed descriptions of adventure activities such as trekking, hiking, camping, and exploring scenic views, making it ideal for travel enthusiasts and tour planners.

	## Model Details

	- Model Type: GPT-2
	- Library: Transformers by Hugging Face
	- Use Case: Text generation focused on adventure travel itineraries
	- Languages: English
	- Base Model: GPT-2
	- Training Data: The model was fine-tuned on a custom dataset of adventure activities in various locations within Sri Lanka's Central Province.

	## How to Use

	You can use this model directly with the Hugging Face Inference API or load it into your Python environment using the Transformers library.

	### Using the Inference API

	You can test the model directly via the Hugging Face platform by clicking on the "Inference API" tab.

	### Using Transformers Pipeline

	```python
	from transformers import pipeline

	# Load the text generation pipeline using the uploaded model from Hugging Face
	generator = pipeline('text-generation', model='yoonusajward01/triptuner')

	# Test the model with a prompt
	response = generator("[Q] Describe an adventure itinerary for Knuckles Mountain Range.", max_length=150, num_return_sequences=1, truncation=True)
	print(response[0]['generated_text'])