Instructions to use papahawk/keya-560m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use papahawk/keya-560m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="papahawk/keya-560m")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("papahawk/keya-560m") model = AutoModelForCausalLM.from_pretrained("papahawk/keya-560m", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use papahawk/keya-560m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "papahawk/keya-560m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "papahawk/keya-560m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/papahawk/keya-560m
- SGLang
How to use papahawk/keya-560m 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 "papahawk/keya-560m" \ --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": "papahawk/keya-560m", "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 "papahawk/keya-560m" \ --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": "papahawk/keya-560m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use papahawk/keya-560m with Docker Model Runner:
docker model run hf.co/papahawk/keya-560m
File size: 862 Bytes
e3a7c05 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 | {% extends 'base.html' %}
{% block title %}
AI Lounge Chat
{% endblock %}
{% block content %}
<div class="chatbot-container">
<div class="chat-header">
<h2>Hello World!</h2>
</div>
<div class="chat-body">
<div class="chat-messages">
<!-- chat messages will be added dynamically using JavaScript -->
</div>
<div class="chat-input">
<form id="chat-form">
<input type="text" id="user-input" placeholder="Type your message...">
<button type="submit" id="send-btn">Send</button>
</form>
</div>
</div>
<h2 class="center"><a href="{{ url_for('home') }}">Back to Home</a></h2>
</div>
<script src="{{ url_for('static', filename='js/chat.js') }}"></script>
{% endblock %}
|