YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
dagformer-scaling-75m-baseline
Dense OLMo-2 75M baseline for DAGFormer scaling study. Public.
- Chinchilla tokens, trained on Dolma v1_7 (books + c4-filtered)
- Final ckpt at repo root in HF format (AutoModelForCausalLM-loadable)
- All saved ckpts under
ckpts/(raw .pt, includes optimizer state)
Load final (recommended)
from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("blackhao0426/dagformer-scaling-75m-baseline")
tok = AutoTokenizer.from_pretrained("blackhao0426/dagformer-scaling-75m-baseline")
- Downloads last month
- 18
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support