Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
llm-course-hw2-dpo – AI Model by Amir337 | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
Amir337
/
llm-course-hw2-dpo
like
0
transformers
safetensors
llama
text-generation
conversational
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
При выполнении этого задания были потрачены 3 коллаба и 1 каггл, обучениее падало примерно 10 раз
Model Card for Model ID
PPO -
https://huggingface.co/Amir337/llm-course-hw2-ppo
reward model:
https://huggingface.co/Amir337/trainer_output
Model Details
image
image