Get a weekly rundown of the latest AI models and research... subscribe!

Llama 2 70b


AI model preview image
The llama-2-70b model is a language model created by Meta. It has 70 billion parameters, making it considerably large and capable of complex tasks. The model's principal function is to enhance and elaborate given prompts, adding detail and specifying the genre or style, such as hyperrealism, art deco, or vector art. The example inputs show prompts related to illustrations and physical appearances being expanded with introductory phrases and additional descriptive terminology. The model's output schema further illustrates these twists and tweaks, displaying a range of improved descriptions based on the original input. Adjustments to key parameters like temperature, repetition_penalty, and top_p can be made to influence the creativity and diversity of the generated output.

Use cases

The Llama-2-70b AI model, a language model with 70 billion parameters developed by Meta, provides refined prompts based on supplied original prompts. The model holds potential in several use cases. One being in the field of digital arts where artists, graphic designers, or art directors could leverage it to generate detailed, innovative, and intricate ideas or themes for creative projects. The highly descriptive, varied vocabulary of this model could catalyze the development of unique artistic concepts that range from psychedelic 3D illustrations to surreal fantasy art. Moreover, the model could see usage in fields like advertising, marketing, or content creation - working as a creative consultant - to provide an improved, detailed interpretation of a central idea. The model could also be utilized in education, aiding in developing vivid, engaging prompts to stimulate critical and creative thinking among students. Furthermore, it could be developed into a specific product, such as an AI-driven creative art or storytelling tool, enabling creators to take a basic concept and transform it into a detailed, imaginative narrative or visual scene. Its vast parameters and quality output hold potential for countless practical applications across various professions and industries.


Cost per run
Avg run time

Creator Models

Codellama 13b Python$?3,775
Codellama 70b Instruct$?13,091
Codellama 34b$?9,519
Codellama 13b$?105,411

Similar Models

No similar models found

Try it!

You can use this area to play around with demo applications that incorporate the Llama 2 70b model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameLlama 2 70b
Base version of Llama 2, a 70 billion parameter language model from Meta.
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkView on Arxiv


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$-
Prediction Hardware-
Average Completion Time-