Llama-3 (15 trillion tokens, GPT3.5 level) is fully supported! Get 2x faster, 60% less VRAM usage than HF + FA2!

Colab notebook: https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing

Pre-quantized 8b and 70b weights (4x faster downloading) via https://huggingface.co/unsloth

What's Changed

• Readme Changes by @danielhanchen in https://github.com/unslothai/unsloth/pull/324
• Tokenizers fix by @danielhanchen in https://github.com/unslothai/unsloth/pull/336
• Update README.md by @danielhanchen in https://github.com/unslothai/unsloth/pull/351
• Update README.md by @danielhanchen in https://github.com/unslothai/unsloth/pull/352

Full Changelog: https://github.com/unslothai/unsloth/compare/April-2024...April-Llama-3-2024