Downloads · 30 days
3
3% of all-time downloads
OLMo-1B-as_fm3_tg_omi2_ppo
rosieyzh/OLMo-1B-as_fm3_tg_omi2_ppo
OLMo-1B-as_fm3_tg_omi2_ppo is a text generation model from rosieyzh. Use it when you need the model to write or continue text. It is set up for transformers.
This is the final checkpoint of the OLMo 1B model pretrained on Algebraic Stack, FineMath3+, TinyGSM, and OpenMathInstruct2 after performing PPO with GSM8K train.
All-time downloads
114
Public
Parameters
1.1B
4.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.6 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- olmo
- Access
- Public
- Created
- Jun 18, 2025
- Updated
- Jun 19, 2025
- SHA
- 598c2f66
Try a prompt
Model card
From the Hugging Face model README
Model Details
This is the final checkpoint of the OLMo 1B model pretrained on Algebraic Stack, FineMath3+, TinyGSM, and OpenMathInstruct2 after performing PPO with GSM8K train.
Checkpoints are saved at the following timesteps:
-
rosieyzh/OLMo-1B-as_fm3_tg_omi2_base: Initial model after pretraining. -
rosieyzh/OLMo-1B-as_fm3_tg_omi2_episode{1-9}: Saved after each epoch over GSM8K train. -
rosieyzh/OLMo-1B-as_fm3_tg_omi2_global_step{9, 13, 18, 25, 36, 51, 73, 103, 146, 206, 291, 411, 581, 821}: Saved on a log scale across global steps (computed from[int(n) for n in np.logspace(-2.1, 0, 15) * 1160]).
Note that the current model, rosieyzh/OLMo-1B-as_fm3_tg_omi2_ppo, is the final model after RLVR and equivalent to _episode10 and _globalstep1160.
- Task
- Text Generation
- Library
- transformers
- Type
- olmo
- Created
- Jun 18, 2025
- Updated
- Jun 19, 2025