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]
@abhi1thakur
-
Finetuned Llama3 Model with AutoTrain Zero Code
By
–
Finetuned llama3 model using AutoTrain: https://
huggingface.co/abhishek/autot
rain-llama3-no-robots
… Amount of code written to finetune: 0 lines -
Finetune Both Variants Using AutoTrain
By
–
You can finetune both variants using AutoTrain: http://
hf.co/autotrain -
LLaMa3 Now Available with AutoTrain No-Code Fine-tuning
By
–
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
-
Create Your Own Competition on Hugging Face Platform
By
–
Use the competition creator space to create your own competition on Hugging Face:
-
Hugging Face Competitions Now Use OAuth Login by Default
By
–
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*
-
80k Models Trained with AutoTrain on Hugging Face Hub
By
–
So, you like numbers? Here's a number for you! More than 80k models on Hugging Face Hub have been trained using AutoTrain And probably tens of thousands of other models which are not on the hub since AutoTrain now allows local training Try it now!
-
Train Mixtral 8x7b Models on DGX Without PEFT
By
–
Now you can train models like Mixtral 8x7b without PEFT on 8xH100s with brand new "Train on DGX" feature on Hugging Face