Jondurbin

Models by this creator

🐍

airoboros-13b

jondurbin

Total Score

106

The airoboros-13b model is a fine-tuned 13-billion parameter LlaMa model, using completely synthetic training data created by jondurbin. It is an experimental model that the maintainer does not recommend using, as the outputs are not particularly great and it may contain "harmful" data due to jailbreaking. For a much better experience, the maintainer recommends using one of the updated airoboros models. The model was evaluated by GPT-4, which provided scores across a variety of tasks. Compared to models like GPT-3.5, GPT-4-x-Alpasta-30B, Manticore-13B, Vicuna-13B-1.1, and Wizard-Vicuna-13B-Uncensored, the airoboros-13b model scored relatively lower on average, with some specific task scores being quite low. Model inputs and outputs Inputs Text prompts**: The model accepts text prompts as input, which can be used to generate continuations or responses. Outputs Text generation**: The primary output of the model is the generation of text, which can be used for a variety of natural language processing tasks. Capabilities The airoboros-13b model is capable of generating text, but the maintainer has warned that the outputs are not particularly great and may contain "harmful" data. The model was outperformed by several other similar models across a range of tasks, as evidenced by the evaluation scores provided. What can I use it for? Given the maintainer's warning about the quality of the outputs and potential for harmful content, it is not recommended to use the airoboros-13b model for any production or real-world applications. The maintainer suggests using one of the updated airoboros models instead, which are likely to provide a much better experience. Things to try As the maintainer has advised against using this model, it is not recommended to experiment with it. Instead, users interested in similar language models should explore the updated airoboros models or other state-of-the-art models that have been more thoroughly vetted and validated.

Read more

Updated 5/28/2024

🤖

bagel-dpo-34b-v0.2

jondurbin

Total Score

96

bagel-dpo-34b-v0.2 is an experimental fine-tune of the yi-34b-200k model by maintainer jondurbin. It was created using the bagel tool and includes the toxic DPO dataset, aiming to produce less censored outputs than similar models. This version may be helpful for users seeking a more uncensored AI assistant. Model Inputs and Outputs Inputs Text prompts and instructions provided to the model Outputs Coherent, open-ended text responses to the provided prompts and instructions Capabilities The bagel-dpo-34b-v0.2 model is capable of generating detailed, uncensored responses to a wide range of prompts and instructions. It demonstrates strong language understanding and generation abilities, and can be used for tasks like creative writing, open-ended dialogue, and even potentially sensitive or controversial topics. What Can I Use It For? The bagel-dpo-34b-v0.2 model could be useful for researchers, developers, or content creators who require a more uncensored AI assistant. It may be applicable for projects involving creative writing, interactive fiction, or even AI-powered chatbots. However, users should exercise caution as the model's outputs may contain sensitive or objectionable content. Things to Try One interesting aspect of the bagel-dpo-34b-v0.2 model is its potential to generate responses on controversial topics that other models may avoid or censor. You could try providing the model with prompts related to sensitive subjects and observe how it responds in an uncensored manner. Just keep in mind that the model's outputs may not always be suitable for all audiences.

Read more

Updated 5/28/2024