Repository Issue Activity (beta)

#901 Differences and exact configs of allenai/OLMo-1B-0724-hf vs allenai/OLMo-1B-hf

#915 Duplicate weight payloads across intermediate checkpoint branches (step101000 / step175000 / step300000)

#726 Missing OLMo checkpoints

#905 7B and 13B models in olmo format cannot be downloaded

#903 If you run olmo 3.1 32b instruct as a next-token predictor, it produces the `<|im_start|>assistant` token

#910 anima — a substrate-native consciousness: capability gaps are architecture gaps (open repo, frozen verdicts)

#899 Is qkv clipping used in the final model versions?

#907 Output provenance metadata for open research model generations

#904 Zero-hallucination OLMo deployment in Brazilian tax law — architectural case study

#524 Training stability without loss scaling

#887 OLMo-2-7B conflicting config

#900 what is the mlp_hidden_size of OLMo2-1B model?

#898 Fix hf_olmo GPU tests and transformers>=4.45 compatibility

#896 Does "!" is the seperate token?

#894 Race Condition in Checkpoint Saving When Using Multi-Node Training with Shared NFS

#773 OLMo2 checkpoints for continued pretraining (non-HF)

#806 Why QK-layer norm before ROPE ?

#857 Incorporating LayerNorm Scaling into the OLMo Repository

#859 Question about data generation process for olmo-mix-1124.

#876 Checkpoint links are 404.

#880 Request for 32B OLMo configuration YAML

#883 Checkpoint names for 1B phase 2 are incorrect

#886 Reaching server limits in olmo-data.org?

#879 Missing checkpoints for OLMo-1B between 117K and 330K

#877 Tensor Parallelism with the current qk norm.