| library_name: peft | |
| base_model: mistralai/Mistral-7B-v0.1 | |
| pipeline_tag: text-generation | |
| Description: Content generation given a headline\ | |
| Original dataset: https://huggingface.co/datasets/JulesBelveze/tldr_news \ | |
| ---\ | |
| Try querying this adapter for free in Lora Land at https://predibase.com/lora-land! \ | |
| The adapter_category is Other and the name is News Content Generation (tldr_news)\ | |
| ---\ | |
| 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.\n\nHeadline: Latest success from Google’s AI group: Controlling a fusion reactor \n\nContent: \ | |
| ---\ | |
| 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.\ | |
| ---\ | |
| Try using this adapter yourself! | |
| ``` | |
| 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) | |
| ``` |