🥀🫩💀 PPO 😭🙏💔

🤓☝️ SmolLM2-135M-Instruct дообучена методом PPO на HumanLLMs/Human-Like-DPO-Dataset. 🧠🔥🫠🥀

😭 RLHF reward: 1.5684. 🙏💔 🫩 KL: 0.2382. 💀🥀

🗿🔥 Пример генерации 😭🙏🥀

What's your morning routine like?

My morning routine is quite simple, but it's essential for maintaining a healthy and productive work-life balance. Here's what I do every morning:

💀🫩🥀🙏

Downloads last month
384
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for youngpin1/llm-course-hw2-ppo

Finetuned
(407)
this model

Dataset used to train youngpin1/llm-course-hw2-ppo