Instruct Llama70B Dolly15k

🚀 Instruct_Llama70B_Dolly15k

This model is fine-tuned from Llama-2-70B using the Dolly15k dataset. It offers high - quality text generation capabilities.

🚀 Quick Start

Instruct_Llama70B_Dolly15k is fine - tuned from Llama - 2 - 70B, using the Dolly15k dataset. The dataset is split as 80% for training, 15% for validation, and 5% for testing. It was trained for 1.5 epochs with QLora and a 1024 context window.

✨ Features

• Fine - Tuned: Based on Llama - 2 - 70B, fine - tuned with the Dolly15k dataset.
• Data Split: Well - structured data split for training, validation, and testing.
• Training Method: Trained using QLora with a 1024 context window.

📚 Documentation

Model Details

Prompting

Prompt Template With Context

Write a 10 - line poem about a given topic

Input:

The topic is about racecars

Output:

Prompt Template Without Context

Who was the was the second president of the United States?

Output:

Professional Assistance

This model and other similar models are great. However, the most potential of LLMs lies in applying them to custom data to automate a wide range of tasks.

If you have a dataset and want to check if you can use it to automate some tasks, and you are seeking professional assistance, contact me here

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

📄 License

The model uses the llama2 license.