Downloads · 30 days
0
olmo3-32b-sft
cbai-eval-awareness/olmo3-32b-sft
olmo3-32b-sft is a machine learning model from cbai-eval-awareness. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Replication of the first 100 steps of AI2's OLMo-3 32B Think-SFT recipe (olmo-core, AI2's pre-tokenized Dolci data, faithful data order). HF-format checkpoints at SFT steps 0, 25, 50, 75, 100, one per subfolder (step0…
Access
Public
Updated Jun 27, 2026
Repo size
322 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors322 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 26, 2026
- Updated
- Jun 27, 2026
- SHA
- ab6bf961
Model card
From the Hugging Face model README
OLMo-3-32B SFT — early-training checkpoints (eval-awareness study)
Replication of the first 100 steps of AI2's OLMo-3 32B Think-SFT recipe (olmo-core,
AI2's pre-tokenized Dolci data, faithful data order). HF-format checkpoints at SFT
steps 0, 25, 50, 75, 100, one per subfolder (step0/ … step100/).
Load a given step:
from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("cbai-eval-awareness/olmo3-32b-sft", subfolder="step50")
Used to trace verbalized eval-awareness (VEA) across early SFT.
- License
- apache-2.0
- Created
- Jun 26, 2026
- Updated
- Jun 27, 2026