CodeLlama 34B-Python Open-Source Model - Free Support for Python Code Generation and Comprehension Tasks

Codellama 34B Python Fp16

Developed by TheBloke

CodeLlama 34B-Python is a large language model with 34B parameters released by Meta, specifically optimized for Python programming. It is improved based on the Llama 2 architecture and supports code generation and understanding tasks.

Large Language Model

Transformers

#Large parameter code generation #Python-specific optimization #Support for 16K long texts

Downloads 196

Release Time : 8/24/2023

Model Overview

This is the 34B parameter version of the CodeLlama series specifically optimized for Python. It uses the fp16 precision weight format and is suitable for tasks such as code synthesis, completion, and understanding. It needs to be loaded with the transformers library using trust_remote_code=True.

Model Features

Python-specific optimization

Designed specifically for the Python language, it performs excellently in tasks such as code completion and syntax understanding

Long context support

Supports up to 16K tokens during training and can handle long codes up to 100K tokens during inference

Commercial availability

Provides a customized commercial license, suitable for enterprise-level application development

Model Capabilities

Python code generation

Code completion

Syntax error detection

Code comment generation

API usage example generation

Use Cases

Development assistance

IDE intelligent plugin

Integrated into the development environment to provide real-time code suggestions

Improve developer efficiency by about 30% (based on internal tests)

Automated code review

Detect code style issues and potential defects

Education

Programming teaching assistant

Generate code examples and practice questions for teaching

🚀 CodeLlama 34B-Python fp16

This repository provides Transformers/HF format fp16 weights for CodeLlama 34B-Python, facilitating easy integration and utilization in relevant projects.

🚀 Quick Start

This is Transformers/HF format fp16 weights for CodeLlama 34B-Python. It is the result of downloading CodeLlama 34B-Python from Meta and converting to HF using convert_llama_weights_to_hf.py.

Quantisations will be coming shortly.

Please note that due to a change in the RoPE Theta value, for correct results you must load these FP16 models with trust_remote_code=True

Credit to @emozilla for creating the necessary modelling code to achieve this!

✨ Features

Model Creator: Meta
Prompt Template: TBC

📚 Documentation

Model Details

Property	Details
Model Developers	Meta AI
Variations	Code Llama comes in three model sizes, and three variants: 1) Code Llama: our base models designed for general code synthesis and understanding 2) Code Llama - Python: designed specifically for Python 3) Code Llama - Instruct: for instruction following and safer deployment All variants are available in sizes of 7B, 13B and 34B parameters.
Input	Models input text only.
Output	Models output text only.
Model Architecture	Code Llama and its variants are autoregressive language models using optimized transformer architectures. Code Llama 7B and 13B additionally support infilling text generation. All models were fine-tuned with up to 16K tokens, and support up to 100K tokens at inference time.
Model Dates	Code Llama and its variants have been trained between January 2023 and July 2023.
Status	This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.
Licence	A custom commercial license is available at: https://ai.meta.com/resources/models-and-libraries/llama-downloads/.
Research Paper	More information can be found in the paper "Code Llama: Open Foundation Models for Code".
Where to send comments	Instructions on how to provide feedback or comments on the model can be found in the model README, or by opening an issue in the GitHub repository (https://github.com/facebookresearch/codellama/).

Intended Use

⚠️ Important Note

Code Llama and its variants should be used in compliance with applicable laws and regulations, and within the scope defined by the Acceptable Use Policy and Licensing Agreement.

Usage Type	Details
Intended Use Cases	Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.
Out-of-Scope Uses	Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.

Usage Type

Details

Intended Use Cases

Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.

Out-of-Scope Uses

Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.

Hardware and Software

Property	Details
Training Factors	We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.
Carbon Footprint	In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.
Training data	All experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the research paper for details). Code Llama - Instruct uses additional instruction fine-tuning data.
Evaluation Results	See evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.

Ethical Considerations and Limitations

⚠️ Important Note

Code Llama and its variants are a new technology that carries risks with use. Before deploying any applications, developers should perform safety testing and tuning tailored to their specific applications.

Code Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.

Please see the Responsible Use Guide available at https://ai.meta.com/llama/responsible-user-guide.

📄 License

This model uses the llama2 license.

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute.

Thanks to the chirper.ai team!

I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.

If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.

Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.

Patreon: https://patreon.com/TheBlokeAI
Ko-Fi: https://ko-fi.com/TheBlokeAI

Special thanks to: Aemon Algiz.

Patreon special mentions: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご