mlabonne/codellama-2-7b
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kLicense:apache-2.0Architecture:Transformer0.0K Open Weights Cold
The mlabonne/codellama-2-7b is a 7 billion parameter Llama 2-based causal language model developed by mlabonne. It is fine-tuned using QLoRA on the mlabonne/CodeLlama-2-20k dataset, specifically optimized for code generation tasks. This model is a Llama 2 version of CodeAlpaca, designed to excel at generating programming code.
Loading preview...
Overview
The mlabonne/codellama-2-7b is a 7 billion parameter language model developed by mlabonne, based on the Llama 2 architecture. It is a specialized version of the llama-2-7b-chat-hf model, fine-tuned using QLoRA on the mlabonne/CodeLlama-2-20k dataset. This model is designed to be a Llama 2 iteration of the CodeAlpaca project, focusing on code-related tasks.
Key Capabilities
- Code Generation: Optimized for generating programming code, as demonstrated by its training on a code-specific dataset.
- Llama 2 Foundation: Benefits from the robust architecture and pre-training of the Llama 2 family of models.
- QLoRA Fine-tuning: Utilizes QLoRA for efficient fine-tuning, making it suitable for deployment on consumer-grade hardware like an RTX 3090.
Good For
- Python Code Generation: Examples provided in the README specifically showcase its ability to generate Python code.
- Code-centric Applications: Ideal for use cases requiring a model specialized in understanding and producing programming language constructs.
- Resource-constrained Environments: Its 7 billion parameter size and QLoRA fine-tuning make it a viable option for environments with limited computational resources.