Pretrained models from scratch used in "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining".
Rosie Zhao
rosieyzh
·
AI & ML interests
theory of machine learning, deep learning
Recent Activity
updated
a dataset
about 17 hours ago
rosieyzh/sonnet3.5_slimorca_500tok
published
a dataset
about 17 hours ago
rosieyzh/sonnet3.5_slimorca_500tok
updated
a dataset
4 days ago
rosieyzh/litbench_500tok
Organizations
OLMo 1B model pretrained with Algebraic Stack, FineMath3, TinyGSM, OMI1, and OMI2. Includes checkpoints from doing PPO using GSM8K train.
-
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_ppo
Text Generation • 1B • Updated • 1 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode1
Text Generation • 1B • Updated • 1 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode2
Text Generation • 1B • Updated -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode3
Text Generation • 1B • Updated • 1
Pretrained models from scratch used in "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining".
OLMo 1B model pretrained with Algebraic Stack, FineMath3, TinyGSM, OMI1, and OMI2. Includes checkpoints from doing PPO using GSM8K train.
-
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_ppo
Text Generation • 1B • Updated • 1 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode1
Text Generation • 1B • Updated • 1 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode2
Text Generation • 1B • Updated -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode3
Text Generation • 1B • Updated • 1
models
93
rosieyzh/finemath4_full_150m
Text Generation
•
0.2B
•
Updated
•
5
rosieyzh/qwen2.5-vl-7b-seed1-step1050
Image-to-Text
•
8B
•
Updated
•
1
rosieyzh/qwen2.5-vl-7b-seed1-step850
Image-to-Text
•
8B
•
Updated
rosieyzh/qwen2.5-vl-7b-seed1-step650
Image-to-Text
•
8B
•
Updated
•
2
rosieyzh/qwen2.5-vl-7b-seed1-step450
Image-to-Text
•
8B
•
Updated
•
1
rosieyzh/qwen2.5-vl-7b-seed1-step250
Image-to-Text
•
8B
•
Updated
•
1
rosieyzh/qwen2.5-vl-7b-augment-seed1-step1050
Image-to-Text
•
8B
•
Updated
•
1
rosieyzh/finemath4_0-15_0.5xchin_150m
Text Generation
•
0.2B
•
Updated
•
3
rosieyzh/finemath4_0-15_0.2xchin_150m
Text Generation
•
0.2B
•
Updated
•
5
rosieyzh/finemath4_0-15_0.1xchin_150m
Text Generation
•
0.2B
•
Updated
•
4
datasets
7
rosieyzh/sonnet3.5_slimorca_500tok
Viewer
•
Updated
•
154k
•
11
rosieyzh/litbench_500tok
Viewer
•
Updated
•
15.9k
•
23
rosieyzh/tinystories_100k_200tok
Viewer
•
Updated
•
101k
•
90
rosieyzh/tinystories_100k
Viewer
•
Updated
•
101k
•
8
rosieyzh/synthetic_spatialmap
Viewer
•
Updated
•
5.5k
•
7
•
1
rosieyzh/synthetic_grid
Viewer
•
Updated
•
5.5k
•
10
•
1
rosieyzh/synthetic_ring
Viewer
•
Updated
•
5.5k
•
12
•
1