sharpbai/Llama-2-13b-chat-hf
The sharpbai/Llama-2-13b-chat-hf model is a 13 billion parameter, fine-tuned generative text model developed by Meta, optimized for dialogue use cases. This Llama 2 variant is converted for the Hugging Face Transformers format and excels in assistant-like chat applications. It utilizes an optimized transformer architecture with supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety, supporting a 4096-token context length.
Loading preview...
Overview
This model, sharpbai/Llama-2-13b-chat-hf, is a 13 billion parameter variant from Meta's Llama 2 family of large language models. It is a fine-tuned version, specifically optimized for dialogue and chat applications, and has been converted for use with Hugging Face Transformers. The model was developed by Meta and trained between January and July 2023, with pretraining data having a cutoff of September 2022.
Key Capabilities
- Dialogue Optimization: Fine-tuned using Supervised Fine-Tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF) to enhance helpfulness and safety in conversational settings.
- Performance: Outperforms many open-source chat models on various benchmarks and achieves competitive results with popular closed-source models in human evaluations for helpfulness and safety.
- Context Length: Supports a context length of 4096 tokens.
- Architecture: Based on an optimized transformer architecture.
Intended Use Cases
- Assistant-like Chat: Primarily designed for commercial and research use in English for assistant-like conversational AI.
- Natural Language Generation: While the chat version is for dialogue, the underlying Llama 2 architecture can be adapted for various natural language generation tasks.