RichardErkhov/stanford-oval_-_Llama-2-7b-WikiChat-fused-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-2-7b-WikiChat-fused - bnb 8bits

• Model creator: https://huggingface.co/stanford-oval/
• Original model: https://huggingface.co/stanford-oval/Llama-2-7b-WikiChat-fused/

Original model description:

license: llama2 language: - en

This model is a fine-tuned LLaMA-2 (7B) model. Please accept the LLaMA-2 license agreement before downloading this model.

Refer to the following for more information:

GitHub repository: https://github.com/stanford-oval/WikiChat

Paper: https://aclanthology.org/2023.findings-emnlp.157/

WikiChat

Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia

Online demo: https://wikichat.genie.stanford.edu