Downloads · 30 days
3
15% of all-time downloads
token-averaging-seed_replicates-avg_50m_k2_seed1
FAIRC/token-averaging-seed_replicates-avg_50m_k2_seed1
token-averaging-seed_replicates-avg_50m_k2_seed1 is a machine learning model from FAIRC. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Checkpoint dump from the token averaging research project.
All-time downloads
20
Public
Repo size
599 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt599 MB · 100%
At a glance
- Access
- Public
- Created
- Sep 14, 2026
- Updated
- Sep 14, 2026
- SHA
- 2bc0dbf1
Model card
From the Hugging Face model README
FAIRC/token-averaging-seed_replicates-avg_50m_k2_seed1
Checkpoint dump from the token averaging research project.
- run name:
avg_50m_k2_seed1 - results tree:
seed_replicates
Contents
Loss logs
loss_log.csv
Checkpoints
checkpoints/final.ptcheckpoints/step_00050000.ptcheckpoints/step_00100000.pt
Loading a checkpoint
import torch
from huggingface_hub import hf_hub_download
path = hf_hub_download('FAIRC/token-averaging-seed_replicates-avg_50m_k2_seed1', 'checkpoints/final.pt')
state = torch.load(path, map_location='cpu', weights_only=False)
model.load_state_dict(state['model']) # your OLMAveraged / OLMTransformerBody
print(state['step'], state['tokens_seen'], state['cumulative_flops'])
These are not Hugging Face transformers weights. Rebuild the
architecture from config.json → model_config (or from
experiments/chinchilla/model_configs.py in the source repo) and load
the raw state_dict.
- Created
- Sep 14, 2026
- Updated
- Sep 14, 2026