Hugging Face's logo

allenai
/
OLMo-1B

Text Generation
Transformers
PyTorch
Safetensors
English
hf_olmo
custom_code
Model card Files
xet
Community
13

add AIBOM

#13
by RiccardoDav - opened
base: refs/heads/main
←
from: refs/pr/13
Discussion Files changed
+120
-0
Files changed (1) hide show
  1. allenai_OLMo-1B.json +120 -0
allenai_OLMo-1B.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bomFormat": "CycloneDX",
3
+ "specVersion": "1.6",
4
+ "serialNumber": "urn:uuid:c7a7cd4d-b598-4466-8f02-1ce70492fd11",
5
+ "version": 1,
6
+ "metadata": {
7
+ "timestamp": "2025-06-05T09:39:19.611048+00:00",
8
+ "component": {
9
+ "type": "machine-learning-model",
10
+ "bom-ref": "allenai/OLMo-1B-9441fd26-4ca0-5e30-91b5-8045c73a1f7c",
11
+ "name": "allenai/OLMo-1B",
12
+ "externalReferences": [
13
+ {
14
+ "url": "https://huggingface.co/allenai/OLMo-1B",
15
+ "type": "documentation"
16
+ }
17
+ ],
18
+ "modelCard": {
19
+ "modelParameters": {
20
+ "task": "text-generation",
21
+ "architectureFamily": "hf_olmo",
22
+ "modelArchitecture": "OLMoForCausalLM",
23
+ "datasets": [
24
+ {
25
+ "ref": "allenai/dolma-1717a952-0159-5eb7-85fb-7ccf03c0a520"
26
+ }
27
+ ]
28
+ },
29
+ "properties": [
30
+ {
31
+ "name": "library_name",
32
+ "value": "transformers"
33
+ }
34
+ ],
35
+ "consideration": {
36
+ "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. -->"
37
+ }
38
+ },
39
+ "authors": [
40
+ {
41
+ "name": "allenai"
42
+ }
43
+ ],
44
+ "licenses": [
45
+ {
46
+ "license": {
47
+ "id": "Apache-2.0",
48
+ "url": "https://spdx.org/licenses/Apache-2.0.html"
49
+ }
50
+ }
51
+ ],
52
+ "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.",
53
+ "tags": [
54
+ "transformers",
55
+ "pytorch",
56
+ "safetensors",
57
+ "hf_olmo",
58
+ "text-generation",
59
+ "custom_code",
60
+ "en",
61
+ "dataset:allenai/dolma",
62
+ "arxiv:2402.00838",
63
+ "arxiv:2302.13971",
64
+ "license:apache-2.0",
65
+ "autotrain_compatible",
66
+ "region:us"
67
+ ]
68
+ }
69
+ },
70
+ "components": [
71
+ {
72
+ "type": "data",
73
+ "bom-ref": "allenai/dolma-1717a952-0159-5eb7-85fb-7ccf03c0a520",
74
+ "name": "allenai/dolma",
75
+ "data": [
76
+ {
77
+ "type": "dataset",
78
+ "bom-ref": "allenai/dolma-1717a952-0159-5eb7-85fb-7ccf03c0a520",
79
+ "name": "allenai/dolma",
80
+ "contents": {
81
+ "url": "https://huggingface.co/datasets/allenai/dolma",
82
+ "properties": [
83
+ {
84
+ "name": "task_categories",
85
+ "value": "text-generation"
86
+ },
87
+ {
88
+ "name": "language",
89
+ "value": "en"
90
+ },
91
+ {
92
+ "name": "size_categories",
93
+ "value": "n>1T"
94
+ },
95
+ {
96
+ "name": "pretty_name",
97
+ "value": "Dolma"
98
+ },
99
+ {
100
+ "name": "license",
101
+ "value": "odc-by"
102
+ }
103
+ ]
104
+ },
105
+ "governance": {
106
+ "owners": [
107
+ {
108
+ "organization": {
109
+ "name": "allenai",
110
+ "url": "https://huggingface.co/allenai"
111
+ }
112
+ }
113
+ ]
114
+ },
115
+ "description": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research"
116
+ }
117
+ ]
118
+ }
119
+ ]
120
+ }