This is the baseline checkpoint for paper: ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind, which is trained with RL but without theory of mind information.

Please refer to our Github Repo for usage details.

Downloads last month
11
Safetensors
Model size
3.4B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for HakHan/Qwen2.5-3B-Instruct-Persuader

Base model

Qwen/Qwen2.5-3B
Finetuned
(564)
this model

Collection including HakHan/Qwen2.5-3B-Instruct-Persuader