L

Llama 2 13b Hf

Developed by meta-llama
Llama 2 is a series of pre-trained and fine-tuned generative text models developed by Meta, ranging from 7 billion to 70 billion parameters. This is the 13B pre-trained model, converted to Hugging Face Transformers format.
Downloads 62.51k
Release Time : 7/13/2023

Model Overview

Llama 2 is a series of pre-trained and fine-tuned generative text models optimized for various natural language generation tasks. The 13B version is a medium-scale variant that balances performance and computational requirements.

Model Features

Optimized Transformer Architecture
Utilizes an optimized autoregressive Transformer architecture for efficient text generation
Large-scale Pre-training
Trained on a mix of 2 trillion tokens from new public online data, providing strong language understanding capabilities
Business-friendly License
Offers a custom commercial license suitable for both business and research purposes
Safety Alignment
Fine-tuned versions are aligned with human preferences through supervised fine-tuning and reinforcement learning from human feedback

Model Capabilities

Text Generation
Language Understanding
Dialogue Generation
Content Creation

Use Cases

Dialogue Systems
Intelligent Assistants
Building chatbot applications similar to assistants
Comparable to closed-source models like ChatGPT and PaLM in human evaluations
Content Generation
Creative Writing
Generating creative content such as stories and poems
Technical Writing
Generating technical documents, reports, etc.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase