Instructions to use Lukamac/PlayPart-AI-Personal-Trainer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lukamac/PlayPart-AI-Personal-Trainer with Transformers:

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

pipe = pipeline("text-generation", model="Lukamac/PlayPart-AI-Personal-Trainer")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Lukamac/PlayPart-AI-Personal-Trainer")
model = AutoModelForCausalLM.from_pretrained("Lukamac/PlayPart-AI-Personal-Trainer")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Lukamac/PlayPart-AI-Personal-Trainer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Lukamac/PlayPart-AI-Personal-Trainer

SGLang

How to use Lukamac/PlayPart-AI-Personal-Trainer 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 "Lukamac/PlayPart-AI-Personal-Trainer" \
    --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": "Lukamac/PlayPart-AI-Personal-Trainer",
		"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 "Lukamac/PlayPart-AI-Personal-Trainer" \
        --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": "Lukamac/PlayPart-AI-Personal-Trainer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Lukamac/PlayPart-AI-Personal-Trainer with Docker Model Runner:
```
docker model run hf.co/Lukamac/PlayPart-AI-Personal-Trainer
```

PlayPart-AI-Personal-Trainer / README.md

Lukamac

Update README.md

085fe19 verified over 1 year ago

1.53 kB

license: apache-2.0
datasets:
  - lizziepika/strava_activities_runs
  - Lukamac/MegaGym_dataset
language:
  - en
metrics:
  - perplexity
  - accuracy
base_model:
  - openai-community/gpt2
pipeline_tag: text-generation
library_name: transformers
tags:
  - gpt2
  - text-generation
  - sports
  - fitness
  - gym

PlayPart AI Personal Trainer Model

This model is a fine-tuned version of GPT-2, specifically trained on sports-related and gym exercise datasets. It is intended to provide text-generation capabilities for answering questions about fitness, sports, workout routines, and providing personalized training suggestions.

Intended Use

Text Generation: Generate text based on sports and fitness questions and interactions.
Personal Trainer Chatbot: Suitable for chatbot integrations focused on fitness, workouts, and sports topics.

Usage

To use the model, you can either use the Hugging Face Inference API or load it in your Python environment.

Example (Python)

from transformers import GPT2Tokenizer, GPT2LMHeadModel

# Load the model
tokenizer = GPT2Tokenizer.from_pretrained("Lukamac/PlayPart-AI-Personal-Trainer")
model = GPT2LMHeadModel.from_pretrained("Lukamac/PlayPart-AI-Personal-Trainer")

# Generate a response
input_text = "What are the best exercises for building upper body strength?"
input_ids = tokenizer.encode(input_text, return_tensors='pt')
output_ids = model.generate(input_ids, max_length=50)
response = tokenizer.decode(output_ids[0], skip_special_tokens=True)

print(response)