Hello. I have a dataset that contains approximately 100 million sentences (2 billion tokens) not in English. I want to implement a model for generating text. Which is better to choose GPT-2 or Llama 3? Approximately with what parameters server needed and how long will it take to train such a model? (so I can count the costs)
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Trying to choose a model/methodology (text generation) | 0 | 390 | April 14, 2021 | |
| Long Text generation | 0 | 686 | May 3, 2021 | |
| Text classification and generation from the same model | 1 | 735 | July 27, 2023 | |
| Text Generation in an Interview-Style with GPT-3 | 1 | 513 | November 4, 2023 | |
| Text generation, LLMs and fine-tuning | 0 | 1637 | December 8, 2022 |