|
--- |
|
base_model: mistralai/Mistral-Nemo-Instruct-2407 |
|
datasets: |
|
- iamtarun/code_instructions_120k_alpaca |
|
language: |
|
- en |
|
library_name: peft |
|
license: apache-2.0 |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# Aurora-12B |
|
Aurora-12B is a powerful language model fine-tuned from the Mistral-Nemo-Instruct-2407 base model, designed specifically for code generation and understanding tasks. This model leverages the extensive iamtarun/code_instructions_120k_alpaca dataset to provide high-quality code-related instructions and solutions. |
|
|
|
## Overview |
|
Aurora-12B is tailored for developers and researchers who need advanced code completion, code understanding, and programming assistance. It understands a wide variety of programming languages and can provide accurate and contextually relevant suggestions. |
|
|
|
## Features |
|
- Code Generation: Generate code snippets in various programming languages. |
|
- Code Completion: Complete partial code fragments. |
|
- Code Understanding: Explain code functionality and provide comments. |
|
- Instruction Following: Follow and execute code-related instructions with high accuracy. |
|
|
|
## Model Details |
|
- Base Model: Mistral-Nemo-Instruct-2407 |
|
- Fine-Tuned On: iamtarun/code_instructions_120k_alpaca |
|
- Parameters: 12 billion |
|
|
|
## Dataset |
|
The model was fine-tuned on the iamtarun/code_instructions_120k_alpaca dataset, which includes 120,000 examples of code instructions and solutions. This diverse dataset ensures that the model can handle a wide range of coding scenarios. |
