Codellama 13b



The model, codellama-13b, is a 13 billion parameter Llama that is specifically tuned for code completion tasks. It uses a text-to-text format and takes in parameters such as debug, top_k, top_p, prompt, temperature, max_new_tokens, min_new_tokens, repetition_penalty, repetition_penalty_sustain, and token_repetition_penalty_decay to produce the completed code. The code generated by this model is based on the input provided and it follows a defined output schema. Its main functionality is to assist in completing partially written code, thereby saving time and effort for the user.

Use cases

The codellama-13b AI model presents a profound capability for code completion, fundamental for enhancing programming efficiency and accuracy. It can be used by software developers who are seeking to streamline their code writing process, especially when tackling complex projects or when learning a new programming language. This model also has potential for broad application in educational settings where it can assist budding programmers in learning by providing real-time coding suggestions as they learn new coding languages or concepts. The model could be used in the development of cutting-edge Integrated Development Environments (IDEs) or in code-related plugins as features to suggest or autocomplete codes in a scope that may cover simple tasks like defining functions to more complex coding tasks. The AI model could also be leveraged in the development of other software applications–ranging from mobile apps, machine learning applications, web apps to other digital platforms– to facilitate faster and reliable coding processes.



Cost per run
Avg run time

Creator Models

Codellama 34b$?6,555
Llama 2 13b$?17,926
Llama 2 13b Chat$?1,592,213
Codellama 7b$?11,084

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Codellama 13b 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 NameCodellama 13b
A 13 billion parameter Llama tuned for code completion
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-