Llama 2 13B Chat Model Overview

This model is the 13 billion parameter variant of Meta's Llama 2 family, specifically fine-tuned for chat and dialogue applications. It leverages an optimized transformer architecture and has undergone extensive supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to enhance its helpfulness and safety for conversational use.

Key Capabilities

Dialogue Optimization: Specifically designed and fine-tuned for assistant-like chat interactions.
Performance: Outperforms many open-source chat models on various benchmarks and achieves parity with some popular closed-source models in human evaluations for helpfulness and safety.
Context Length: Supports a context length of 4096 tokens.
Training Data: Pretrained on 2 trillion tokens of publicly available data, with fine-tuning data including over one million human-annotated examples.

Intended Use Cases

This model is primarily intended for commercial and research use in English for assistant-like chat applications. Developers should follow specific formatting guidelines, including INST and <<SYS>> tags, for optimal performance in chat scenarios. It is not intended for use in languages other than English or in any manner violating its custom commercial license and acceptable use policy.