Tldr Content Gen

🚀 PEFT

A text generation adapter for content generation based on headlines, leveraging the Mistral-7B-v0.1 base model.

🚀 Quick Start

This adapter is designed for content generation given a headline. You can try querying it for free in Lora Land at https://predibase.com/lora-land.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mistral-7B-v0.1"
peft_model_id = "predibase/tldr_content_gen"

model = AutoModelForCausalLM.from_pretrained(model_id)
model.load_adapter(peft_model_id)

Sample Input and Output

Sample Input

The following headline is the headline of a news report. Please write the content of the news passage based on only this headline.

Headline: Latest success from Google’s AI group: Controlling a fusion reactor

Content: 

Sample Output

Google's AI group has developed a system that can control a fusion reactor. The system uses a deep reinforcement learning algorithm to control the reactor's magnetic field. It can control the reactor's magnetic field with a precision of 0.001%. The system can also learn to control the reactor's plasma. A video is available that shows the system controlling the reactor.

📚 Documentation

Adapter Information

💡 Usage Tip

Try using this adapter yourself with the provided code example!