Mem-0
MemAgent-PTE-Qwen3-30B-A3Bmempet_-_merged_gemma_squad_005_synup1-ggufmempet_-_merged_gemma_sharegpt_005_synup-ggufllada-8b-dllm-memory-tokens-mix60k-recon-w005mempet_-_merged_gemma_math_005_synup1-ggufmempet_-_merged_gemma_xlsum_005_synup1-ggufmempet_-_merged_gemma_medqa_refactor_005_synup1-ggufmempet_-_merged_gemma_recipe_005_synup4-gguf
Datasets
All datasets matching “Mem-0”Mem-0-m1mix-dataset-RMBench
Mem-0 m1_mix — RMBench / RoboTwin 2.0 (LeRobot dataset)
The m1_mix training dataset for the Mem-0 execution module: the five RMBench
M1 tasks merged into a single LeRobot
v2.1 dataset with globally unique episode indices. This is the exact data used to
train the checkpoint released at
qiuly/Mem-0-m1mix-RMBench.
Summary
Format
LeRobot v2.1
Episodes
250 (50 per task × 5 tasks)
Frames
92,520
FPS
30
Tasks
5 (see below)
Robot
dual-arm (2× 7-DoF +… See the full description on the dataset page: https://huggingface.co/datasets/qiuly/Mem-0-m1mix-dataset-RMBench.dolphinbench
DolphinBench
DolphinBench measures whether an agent can use long-term memory to take the right actions on a user's behalf. It contains three synthetic users, approximately 500,000 tokens of history per user, and 600 tool-using tests across their work and personal lives.
The benchmark grades the actions an agent takes through simulated apps, not just what it says it remembers.
Load the dataset
from datasets import load_dataset
messages =… See the full description on the dataset page: https://huggingface.co/datasets/mem0ai/dolphinbench.