Festivus

policy

DeepSeek-Prover-V1.5-RL

deepseek-ai · PyTorch

or hover any field below to flag it

Overview

Name
DeepSeek-Prover-V1.5-RL
Author
deepseek-ai
Framework
PyTorch
License
other
Skill type
other
Evidence level
reported
Task description
Policy model from deepseek-ai. Tags: safetensors, llama, arxiv:2408.08152, base_model:deepseek-ai/DeepSeek-Prover-V1.5-SFT, base_model:finetune:deepseek-ai/DeepSeek-Prover-V1.5-SFT.

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
deepseek-ai/DeepSeek-Prover-V1.5-RL
Paper (arXiv)
https://arxiv.org/abs/2408.08152

Compatible robots

3+17 mentioned but not in catalog yet
SpotBoston DynamicsT1Booster RoboticsApolloApptronik

Compatible environments

0

No environments list DeepSeek-Prover-V1.5-RL yet.

Datasets that reference this policy

0

No datasets reference DeepSeek-Prover-V1.5-RL yet.