| Property | Value |
|---|---|
| Author | Xenova |
| Downloads | 30,814 |
| Framework | Transformers.js, PyTorch, ONNX |
| Primary Use | Text Generation |
What is llama2.c-stories15M?
llama2.c-stories15M is a compact implementation of the LLaMA2 architecture specifically optimized for story generation and creative text tasks. Built by Xenova, this model stands out for its browser-compatibility through Transformers.js, making it ideal for client-side applications.
Implementation Details
The model is implemented using Transformers.js, allowing for seamless integration into web applications. It leverages the LLaMA2 architecture in a compressed 15M parameter format, optimized for efficiency while maintaining creative text generation capabilities.
- Built on the Transformers.js framework
- Supports ONNX runtime for optimized inference
- Compatible with PyTorch ecosystem
- Lightweight 15M parameter implementation
Core Capabilities
- Story generation from prompts
- Contextual text completion
- Browser-based inference
- Efficient memory usage
- Customizable generation parameters
Frequently Asked Questions
Q: What makes this model unique?
This model's uniqueness lies in its efficient implementation of LLaMA2 architecture optimized for browser environments, making it ideal for client-side story generation tasks without requiring server infrastructure.
Q: What are the recommended use cases?
The model is best suited for creative writing applications, story generation, and interactive text-based experiences where lightweight, browser-based inference is required. It's particularly effective for generating short stories and narrative continuations.