CodeLlama Models

**Overview**

The Codellama models are large language models (LLMs) developed by Meta AI. The models provided in this listing are

- [CodeLlama_13b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf)
- [CodeLlama_13b_Python_hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf)
- [CodeLlama_13b_hf](https://huggingface.co/codellama/CodeLlama-13b-hf)
- [CodeLlama_34b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf)
- [CodeLlama_34b_Python_hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf)
- [CodeLlama_34b_hf](https://huggingface.co/codellama/CodeLlama-34b-hf)
- [CodeLlama_70b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf)
- [CodeLlama_70b_Python_hf](https://huggingface.co/codellama/CodeLlama-70b-Python-hf)
- [CodeLlama_70b_hf](https://huggingface.co/codellama/CodeLlama-70b-hf)
- [CodeLlama_7b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf)
- [CodeLlama_7b_Python_hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf)
- [CodeLlama_7b_hf](https://huggingface.co/codellama/CodeLlama-7b-hf)

The models are packaged using MLflow’s transformers flavor.
- [CodeLlama_13b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf), [CodeLlama_34b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf), [CodeLlama_70b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf), [CodeLlama_7b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf): fine-tuned for short-form instruction following.
- [CodeLlama_13b_Python_hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf), [CodeLlama_34b_Python_hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf), [CodeLlama_70b_Python_hf](https://huggingface.co/codellama/CodeLlama-70b-Python-hf), [CodeLlama_7b_Python_hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf): fine-tuned for short-form instruction following.
- [CodeLlama_13b_hf](https://huggingface.co/codellama/CodeLlama-13b-hf), [CodeLlama_34b_hf](https://huggingface.co/codellama/CodeLlama-34b-hf), [CodeLlama_70b_hf](https://huggingface.co/codellama/CodeLlama-70b-hf), [CodeLlama_7b_hf](https://huggingface.co/codellama/CodeLlama-7b-hf): fine-tuned for short-form instruction following.

Codellama models are licensed under the [LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved](https://ai.meta.com/resources/models-and-libraries/llama-downloads/). By installing this listing, you acknowledge and agree to the license.

For example notebooks of using the codellama model in various use cases on Databricks, refer to [the Databricks ML example repository](https://github.com/databricks/databricks-ml-examples/tree/master/llm-models/code_generation/codellama).

**Use cases**

[CodeLlama_13b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf), [CodeLlama_34b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf), [CodeLlama_70b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-70b-Instruct-hf), [CodeLlama_7b_Instruct_hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf):
- It is for instruction following and safer deployment.

[CodeLlama_13b_Python_hf](https://huggingface.co/codellama/CodeLlama-13b-Python-hf), [CodeLlama_34b_Python_hf](https://huggingface.co/codellama/CodeLlama-34b-Python-hf), [CodeLlama_70b_Python_hf](https://huggingface.co/codellama/CodeLlama-70b-Python-hf), [CodeLlama_7b_Python_hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf):
- It is a base models specifically for Python code synthesis and understanding.

[CodeLlama_13b_hf](https://huggingface.co/codellama/CodeLlama-13b-hf), [CodeLlama_34b_hf](https://huggingface.co/codellama/CodeLlama-34b-hf), [CodeLlama_70b_hf](https://huggingface.co/codellama/CodeLlama-70b-hf), [CodeLlama_7b_hf](https://huggingface.co/codellama/CodeLlama-7b-hf):
- It is a base models designed for general code synthesis and understanding.

**Product details**

The pre-trained model can be used for further fine-tuning on specific applications. The fine-tuned model in this listing can be deployed directly to Databricks Model Serving for immediate use, or loaded for fine-tuning or batch inference use cases. For more details, install the listing and view the provided model cards for each model.

搜集汇总

背景与挑战

背景概述

该数据集提供Meta AI研发的CodeLlama系列大语言模型，包含7b至70b四种参数规模的基础版、Python专用版和指令调优版共12个变体，采用MLflow封装并适用于代码生成与理解任务，遵循LLAMA 2开源许可协议。