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
3 days ago
rosieyzh/tinystories_100k_200tok
published
a dataset
3 days ago
rosieyzh/tinystories_100k_200tok
updated
a dataset
3 days ago
rosieyzh/tinystories_100k
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 • 5 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode1
Text Generation • 1B • Updated • 3 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode2
Text Generation • 1B • Updated • 3 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode3
Text Generation • 1B • Updated • 3
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 • 5 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode1
Text Generation • 1B • Updated • 3 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode2
Text Generation • 1B • Updated • 3 -
rosieyzh/OLMo-1B-as_fm3_tg_omi1_omi2_episode3
Text Generation • 1B • Updated • 3
models
93
rosieyzh/finemath4_full_150m
Text Generation
•
0.2B
•
Updated
•
7
rosieyzh/qwen2.5-vl-7b-seed1-step1050
Image-to-Text
•
8B
•
Updated
•
4
rosieyzh/qwen2.5-vl-7b-seed1-step850
Image-to-Text
•
8B
•
Updated
•
3
rosieyzh/qwen2.5-vl-7b-seed1-step650
Image-to-Text
•
8B
•
Updated
•
5
rosieyzh/qwen2.5-vl-7b-seed1-step450
Image-to-Text
•
8B
•
Updated
•
4
rosieyzh/qwen2.5-vl-7b-seed1-step250
Image-to-Text
•
8B
•
Updated
•
2
rosieyzh/qwen2.5-vl-7b-augment-seed1-step1050
Image-to-Text
•
8B
•
Updated
•
6
rosieyzh/finemath4_0-15_0.5xchin_150m
Text Generation
•
0.2B
•
Updated
•
6
rosieyzh/finemath4_0-15_0.2xchin_150m
Text Generation
•
0.2B
•
Updated
•
7
rosieyzh/finemath4_0-15_0.1xchin_150m
Text Generation
•
0.2B
•
Updated
•
7