AutoTrain finetuned llama3 beats the base instruct model on all but one benchmark on the open llm leaderboard 🚀 This model was finetuned using ORPO and is also publicly available. No code was written and all the setup took less than 10mins. 🤗 `pip install autotrain-advanced`

Me finetuning llama3 70b on google colab 🤣

AutoTrain just added LLM ORPO as a task! ORPO provides the same performance as DPO with 50% reduction in memory since no reference model is needed 💥 Now, train your own zephyr-orpo like models without writing a single line of code 🚀 [powered by trl]

github.com/huggingface/au…

You can already autotrain (no code needed) Llama3 on NVIDIA DGX cloud thanks to our new integration 🔥🔥🔥

we just shipped HuggingChat on iOS 💬

The app is super polished and gives you access to the community's best open AI models, on the go.

Give it a try!

link to Appstore below ⤵️

Not everyone is aware but the fact that llama3 has been added to HF on day one means that right away, you can easily run it on @aws Sagemaker, @microsoft AzureML, Google Cloud Vertex and the Hugging Face hosted solutions (autotrain, spaces, serverless and dedicated endpoints).

We should send rockets not at each other, but rather to the stars

huggingface.co/posts/abhishek…

Finetuned llama3 model using AutoTrain: huggingface.co/abhishek/autot…
Amount of code written to finetune: 0 lines

LLaMa3 is here! 💥 and AutoTrain already supports it; which means you can fine-tune your LLaMa3 models effortlessly – whether it's locally or on Hugging Face Spaces. Tailor LLaMA 3 to your specific needs by fine tuning it using AutoTrain without writing a single line of code 🚀

Use the competition creator space to create your own competition on Hugging Face: huggingface.co/spaces/competi…

All Hugging Face Competitions use OAuth by default now! No more copy-pasting tokens! Just click 'Login with Hugging Face' and you are ready to compete and win! 🚀
Hosts can organize a competition for FREE*