gbenonvi/Llama-2-7b-chat-hf

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kArchitecture:Transformer Cold

gbenonvi/Llama-2-7b-chat-hf is a 7 billion parameter Llama 2 model developed by Meta, fine-tuned for dialogue use cases and optimized for chat applications. This auto-regressive language model utilizes an optimized transformer architecture and has a context length of 4096 tokens. It is specifically designed for assistant-like chat in English, outperforming many open-source chat models on benchmarks for helpfulness and safety.

Loading preview...

Overview

This model, gbenonvi/Llama-2-7b-chat-hf, is a 7 billion parameter variant from Meta's Llama 2 family of large language models. It is a fine-tuned, instruction-following model specifically optimized for dialogue and chat applications, converted for use with Hugging Face Transformers. The Llama 2 models were trained on a new mix of publicly available online data, totaling 2 trillion tokens, with fine-tuning data including over one million human-annotated examples.

Key Capabilities

  • Dialogue Optimization: Specifically fine-tuned (using SFT and RLHF) for assistant-like chat, aiming for human preferences in helpfulness and safety.
  • Performance: Llama-2-Chat models are reported to outperform other open-source chat models on various benchmarks and achieve parity with some popular closed-source models like ChatGPT and PaLM in human evaluations for helpfulness and safety.
  • Context Length: Supports a context length of 4096 tokens.
  • Safety: Fine-tuned versions show significantly improved safety metrics, achieving 0.00% toxic generations on ToxiGen for the 7B and 13B chat models.

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. It is not intended for use in languages other than English or in ways that violate its commercial license and acceptable use policy.