Instructions to use ajc2195/parks-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ajc2195/parks-llm with Transformers:

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

pipe = pipeline("text-generation", model="ajc2195/parks-llm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ajc2195/parks-llm")
model = AutoModelForCausalLM.from_pretrained("ajc2195/parks-llm")
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 ajc2195/parks-llm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ajc2195/parks-llm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ajc2195/parks-llm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ajc2195/parks-llm

SGLang

How to use ajc2195/parks-llm 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 "ajc2195/parks-llm" \
    --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": "ajc2195/parks-llm",
		"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 "ajc2195/parks-llm" \
        --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": "ajc2195/parks-llm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ajc2195/parks-llm with Docker Model Runner:
```
docker model run hf.co/ajc2195/parks-llm
```

Parks LLM - US Parks Assistant 🏞️

A conversational AI model fine-tuned to help with US national parks, state parks, and recreation areas.

Quick Start

Load the model:

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained("ajc2195/parks-llm")
model = AutoModelForCausalLM.from_pretrained("ajc2195/parks-llm")

def ask_parks_llm(question):
    prompt = f"Human: {question}\nAssistant:"
    inputs = tokenizer(prompt, return_tensors="pt")
    
    with torch.no_grad():
        outputs = model.generate(
            inputs['input_ids'],
            max_new_tokens=80,
            temperature=0.7,
            do_sample=True,
            pad_token_id=tokenizer.eos_token_id
        )
    
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response.split("Assistant:")[-1].strip()

Example usage:

answer = ask_parks_llm("What should I pack for Yellowstone?")
print(answer)

Pipeline Usage

from transformers import pipeline

parks_assistant = pipeline("text-generation", model="ajc2195/parks-llm")
response = parks_assistant("Human: What's the best time to visit national parks?\nAssistant:")

Capabilities

🏞️ Park Information: Details about national parks, state parks, and recreation areas
🎒 Trip Planning: Packing lists, preparation advice, and logistics
📅 Timing Advice: Best times to visit different parks
🏕️ Camping & Reservations: Booking guidance and accommodation options
👨‍👩‍👧‍👦 Family Travel: Family-friendly park recommendations
💰 Budget Tips: Cost-saving strategies
🐻 Safety Guidance: Wildlife safety and Leave No Trace principles
🥾 Activities: Hiking, camping, and outdoor activity recommendations

Example Questions

What should I pack for a desert park visit?
How do I make campground reservations?
What are the best family-friendly national parks?
When is the best time to visit Yellowstone?
What budget tips do you have for park visits?

Model Details

Base Model: microsoft/DialoGPT-medium
Fine-tuned on: Comprehensive parks conversation dataset
Training Method: Manual PyTorch fine-tuning
Domain: US Parks and Recreation

Limitations

Focuses primarily on US parks
General guidance - always verify with official park sources
Not a substitute for real-time park information or alerts

Built with ❤️ for park enthusiasts and outdoor adventurers!

Downloads last month: 2

Model tree for ajc2195/parks-llm

Base model

microsoft/DialoGPT-medium

Finetuned

(93)

this model