RTO-RL
/

Llama3-8B-PPO

Model card Files Files and versions Community

Base Model: OpenRLHF/Llama-3-8b-sft-mixture

Reward model: RTO-RL/Llama3-8B-RewardModel

Prompt dataset: weqweasdas/ultra_train

Downloads last month: 3

Safetensors

Model size

8.03B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for RTO-RL/Llama3-8B-PPO

Base model

OpenRLHF/Llama-3-8b-sft-mixture

Finetuned

(9)

this model

Quantizations

1 model

Dataset used to train RTO-RL/Llama3-8B-PPO