allenai_OLMo-1B.json

{
    "bomFormat": "CycloneDX",
    "specVersion": "1.6",
    "serialNumber": "urn:uuid:c7a7cd4d-b598-4466-8f02-1ce70492fd11",
    "version": 1,
    "metadata": {
        "timestamp": "2025-06-05T09:39:19.611048+00:00",
        "component": {
            "type": "machine-learning-model",
            "bom-ref": "allenai/OLMo-1B-9441fd26-4ca0-5e30-91b5-8045c73a1f7c",
            "name": "allenai/OLMo-1B",
            "externalReferences": [
                {
                    "url": "https://huggingface.co/allenai/OLMo-1B",
                    "type": "documentation"
                }
            ],
            "modelCard": {
                "modelParameters": {
                    "task": "text-generation",
                    "architectureFamily": "hf_olmo",
                    "modelArchitecture": "OLMoForCausalLM",
                    "datasets": [
                        {
                            "ref": "allenai/dolma-1717a952-0159-5eb7-85fb-7ccf03c0a520"
                        }
                    ]
                },
                "properties": [
                    {
                        "name": "library_name",
                        "value": "transformers"
                    }
                ],
                "consideration": {
                    "useCases": "<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->"
                }
            },
            "authors": [
                {
                    "name": "allenai"
                }
            ],
            "licenses": [
                {
                    "license": {
                        "id": "Apache-2.0",
                        "url": "https://spdx.org/licenses/Apache-2.0.html"
                    }
                }
            ],
            "description": "The core models released in this batch are the following:| Size | Training Tokens | Layers | Hidden Size | Attention Heads | Context Length ||------|--------|---------|-------------|-----------------|----------------|| [OLMo 1B](https://huggingface.co/allenai/OLMo-1B)   | 3 Trillion |16     | 2048        | 16              | 2048  || [OLMo 7B](https://huggingface.co/allenai/OLMo-7B) | 2.5 Trillion   | 32     | 4096        | 32              |  2048  || [OLMo 7B Twin 2T](https://huggingface.co/allenai/OLMo-7B-Twin-2T) | 2 Trillion   | 32     | 4096        | 32              |  2048  |We are releasing many checkpoints for these models, for every 1000 traing steps.The naming convention is `step1000-tokens4B`.In particular, we focus on four revisions of the 7B models:| Name | HF Repo | Model Revision |  Tokens | Note ||------------|---------|----------------|-------------------|------||OLMo 7B| [allenai/OLMo-7B](https://huggingface.co/allenai/OLMo-7B)|`main`| 2.5T|The base OLMo 7B model||OLMo 7B (not annealed)|[allenai/OLMo-7B](https://huggingface.co/allenai/OLMo-7B)|step556000-tokens2460B|2.5T| learning rate not annealed to 0||OLMo 7B-2T|[allenai/OLMo-7B](https://huggingface.co/allenai/OLMo-7B)| step452000-tokens2000B |2T| OLMo checkpoint at 2T tokens||OLMo-7B-Twin-2T|[allenai/OLMo-7B-Twin-2T](https://huggingface.co/allenai/OLMo-7B-Twin-2T)|`main`|2T| Twin version on different hardware|To load a specific model revision with HuggingFace, simply add the argument `revision`:```bashfrom hf_olmo import OLMoForCausalLM  # pip install ai2-olmoolmo = OLMoForCausalLM.from_pretrained(\"allenai/OLMo-1B\", revision=\"step20000-tokens84B\")```All revisions/branches are listed in the file `revisions.txt`.Or, you can access all the revisions for the models via the following code snippet:```pythonfrom huggingface_hub import list_repo_refsout = list_repo_refs(\"allenai/OLMo-1B\")branches = [b.name for b in out.branches]```A few revisions were lost due to an error, but the vast majority are present.",
            "tags": [
                "transformers",
                "pytorch",
                "safetensors",
                "hf_olmo",
                "text-generation",
                "custom_code",
                "en",
                "dataset:allenai/dolma",
                "arxiv:2402.00838",
                "arxiv:2302.13971",
                "license:apache-2.0",
                "autotrain_compatible",
                "region:us"
            ]
        }
    },
    "components": [
        {
            "type": "data",
            "bom-ref": "allenai/dolma-1717a952-0159-5eb7-85fb-7ccf03c0a520",
            "name": "allenai/dolma",
            "data": [
                {
                    "type": "dataset",
                    "bom-ref": "allenai/dolma-1717a952-0159-5eb7-85fb-7ccf03c0a520",
                    "name": "allenai/dolma",
                    "contents": {
                        "url": "https://huggingface.co/datasets/allenai/dolma",
                        "properties": [
                            {
                                "name": "task_categories",
                                "value": "text-generation"
                            },
                            {
                                "name": "language",
                                "value": "en"
                            },
                            {
                                "name": "size_categories",
                                "value": "n>1T"
                            },
                            {
                                "name": "pretty_name",
                                "value": "Dolma"
                            },
                            {
                                "name": "license",
                                "value": "odc-by"
                            }
                        ]
                    },
                    "governance": {
                        "owners": [
                            {
                                "organization": {
                                    "name": "allenai",
                                    "url": "https://huggingface.co/allenai"
                                }
                            }
                        ]
                    },
                    "description": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research"
                }
            ]
        }
    ]
}