Codellama 34b Instruct Hf

🚀 Code Llama

Code Llama is a collection of generative text models. These models, with parameters ranging from 7 billion to 34 billion, are pretrained and fine - tuned. This repository is for the 34B instruct - tuned version in the Hugging Face Transformers format, designed for general code synthesis and understanding. You can find links to other models at the bottom.

🚀 Quick Start

To use this model, you need to install the transformers library. You can do this by running the following command:

pip install transformers accelerate

✨ Features

• Code Completion: The model can assist in completing code snippets.
• Instruction Following: It can follow instructions and be used in chat - based scenarios.

📦 Model Details

📚 Intended Use

Intended Use Cases

Code Llama and its variants are for commercial and research use in English and relevant programming languages. The base model can handle various code tasks, the Python variant is for Python programming, and the Instruct variant is safer for code assistant and generation applications.

Out - of - Scope Uses

• Using the model in a way that violates applicable laws or regulations.
• Using languages other than English.
• Any use prohibited by the Acceptable Use Policy and Licensing Agreement.

🔧 Hardware and Software

Training Factors

Custom training libraries were used, and the models were trained and fine - tuned on Meta’s Research Super Cluster.

Carbon Footprint

Training all 9 Code Llama models needed 400K GPU hours on A100 - 80GB hardware. The estimated total emissions were 65.3 tCO2eq, all offset by Meta’s sustainability program.

📊 Training Data

All experiments and released models were trained and fine - tuned using the same data as Llama 2 with different weights. See the research paper for details.

📈 Evaluation Results

Refer to the research paper for evaluations of the main models, detailed ablations, and safety evaluations.

⚠️ Ethical Considerations and Limitations

Code Llama and its variants are new technologies with risks. Testing has been in English and cannot cover all scenarios. The model may produce inaccurate or objectionable responses. Developers should conduct safety testing and tuning for specific applications before deployment. See the Responsible Use Guide at https://ai.meta.com/llama/responsible-use-guide.

⚠️ Important Note This is a non - official Code Llama repo. You can find the official Meta repository in the Meta Llama organization.