metadata

tags:
  - generated_from_trainer
  - conversational
  - mistral
license: mit
language:
  - en
base_model: HuggingFaceH4/zephyr-7b-alpha
library_name: transformers
pipeline_tag: text-generation

Zephyr 7B Alpha-GGUF

Model creator: Hugging Face H4
Original model: Zephyr 7B Alpha

Description

Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-α is the first model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO). We found that removing the in-built alignment of these datasets boosted performance on MT Bench and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so.

Model type: A 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets.
Language(s) (NLP): Primarily English
License: MIT
Finetuned from model: mistralai/Mistral-7B-v0.1