

<div class="card">
<div class="card-body">
<small class="text-muted p-0 m-0">via cs.berkeley.edu on Jul 28, 2023<a href="https://gorilla.cs.berkeley.edu/"> <svg xmlns="http://www.w3.org/2000/svg" width="16" height="16" fill="currentColor" class="bi bi-link-45deg" viewBox="0 0 16 16">
  <path d="M4.715 6.542 3.343 7.914a3 3 0 1 0 4.243 4.243l1.828-1.829A3 3 0 0 0 8.586 5.5L8 6.086a1.002 1.002 0 0 0-.154.199 2 2 0 0 1 .861 3.337L6.88 11.45a2 2 0 1 1-2.83-2.83l.793-.792a4.018 4.018 0 0 1-.128-1.287z"/>
  <path d="M6.586 4.672A3 3 0 0 0 7.414 9.5l.775-.776a2 2 0 0 1-.896-3.346L9.12 3.55a2 2 0 1 1 2.83 2.83l-.793.792c.112.42.155.855.128 1.287l1.372-1.372a3 3 0 1 0-4.243-4.243L6.586 4.672z"/>
</svg></a></small>
<p class="card-text h6">🦍 Gorilla: Large Language Model Connected with Massive APIs</p>
<p class="card-text">Gorilla is a LLM that can provide appropriate API calls. It is trained on three massive machine learning hub datasets: Torch Hub, TensorFlow Hub and HuggingFace. We are rapidly adding new domains, including Kubernetes, GCP, AWS, OpenAPI, and more. Zero-shot Gorilla outperforms GPT-4, Chat-GPT and Claude. Gorilla is extremely reliable, and significantly reduces hallucination errors.
</p>
</div>
</div>