Codellama 13b



The model, codellama-13b, is a 13 billion parameter Llama trained for code completion. It takes in a range of 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 code and construct scripts. The output of this model is code that performs the task described in the inputted prompt. For instance, given a prompt to sum two integers, it writes the appropriate Python function along with user-input and execution instructions.

Use cases

The codellama-13b is an AI model designed for code completion. With a whopping 13 billion parameters, this model is poised to have a significant impact on software development and programming. Its use could span a spectrum of applications where speed and accuracy of coding are essential. For instance, it could be integrated as a feature in Integrated Development Environments (IDEs) to help developers code more quickly and with less errors, a boon especially for novices in programming. Furthermore, it could be utilized in educational platforms to aid students in learning and comprehending various programming languages. Similarly, it could find its application in online coding competitions by recommending possible code completions to the contestants. Furthermore, the model could be used in automated software testing tools to generate or complete chunks of testing code effectively, thereby saving time and resources. Additionally, tech companies can use this model to moderate or review the quality of code generated by their developers by validating against the code completions proposed by the model.



Cost per run
Avg run time

Creator Models

Codellama 34b$?6,555
Llama 2 13b$?17,926
Llama 2 13b Chat$?1,592,213
Codellama 13b$?71,820

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-