Badass Zephyr-7B-β is the second model in the Zephyr series of language models that are trained to act as helpful assistants. It 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).
Supported context length
Price for prompt tokens*
Price for response tokens*
*Note: Data based on 11/14/2023
Here's how Zephyr-7b-beta performed across all three task types
Digging deeper, here’s a look how Zephyr-7b-beta performed across specific datasets
|Tasks||Insights||Dataset Name||Dataset Performance|
|QA without RAG||The model makes quite a mistakes which show bias and errors in factual knowledge.||Truthful QA|
|QA with RAG||Even with small size the model performs commendable which demonstrates great reasoning and comprehension skills. It struggles a bit on mathematical skills as it scores relatively low on DROP compared to other dataset.||MS Marco|
|Long form text generation||The model performs satisfactory at this task which shows good ability to generate long text without factual errors.||Open Assistant|
💰 Cost insights
The model offers a decent balance of cost and performance. It is 13x cheaper compared to GPT3.5 and 6x cheaper compared to Llama 70b variant. We suggest using this instead of Mistral-7b-instruct-v0.1 & Llama-2-7b-chat.