Hugging Face's logo

TinyLlama
/
TinyLlama-1.1B-intermediate-step-1431k-3T

Text Generation
Transformers
PyTorch
Safetensors
English
llama
Eval Results
text-generation-inference
Model card Files
xet
Community
11

add AIBOM

#11
by RiccardoDav - opened
base: refs/heads/main
←
from: refs/pr/11
Discussion Files changed
+206
-0
Files changed (1) hide show
  1. TinyLlama_TinyLlama-1.1B-intermediate-step-1431k-3T.json +206 -0
TinyLlama_TinyLlama-1.1B-intermediate-step-1431k-3T.json ADDED
@@ -0,0 +1,206 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bomFormat": "CycloneDX",
3
+ "specVersion": "1.6",
4
+ "serialNumber": "urn:uuid:84dcbcb5-128b-48fa-ac83-877bc829a20f",
5
+ "version": 1,
6
+ "metadata": {
7
+ "timestamp": "2025-10-23T16:24:20.040807+00:00",
8
+ "component": {
9
+ "type": "machine-learning-model",
10
+ "bom-ref": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T-18d39ff6-e8f5-527a-9461-dd57145354aa",
11
+ "licenses": [
12
+ {
13
+ "license": {
14
+ "id": "Apache-2.0",
15
+ "url": "https://spdx.org/licenses/Apache-2.0.html"
16
+ }
17
+ }
18
+ ],
19
+ "externalReferences": [
20
+ {
21
+ "url": "https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
22
+ "type": "documentation"
23
+ }
24
+ ],
25
+ "modelCard": {
26
+ "modelParameters": {
27
+ "datasets": [
28
+ {
29
+ "ref": "cerebras/SlimPajama-627B-b36a2f54-050e-55dd-bb65-57b90579dbe6"
30
+ },
31
+ {
32
+ "ref": "bigcode/starcoderdata-abfd2d2a-390d-56b4-ad9c-c532362d5827"
33
+ }
34
+ ],
35
+ "task": "text-generation",
36
+ "architectureFamily": "llama",
37
+ "modelArchitecture": "LlamaForCausalLM"
38
+ },
39
+ "properties": [
40
+ {
41
+ "name": "library_name",
42
+ "value": "transformers"
43
+ }
44
+ ],
45
+ "quantitativeAnalysis": {
46
+ "performanceMetrics": [
47
+ {
48
+ "slice": "dataset: ai2_arc, split: test, config: ARC-Challenge",
49
+ "type": "acc_norm",
50
+ "value": 33.87
51
+ },
52
+ {
53
+ "slice": "dataset: hellaswag, split: validation",
54
+ "type": "acc_norm",
55
+ "value": 60.31
56
+ },
57
+ {
58
+ "slice": "dataset: cais/mmlu, split: test, config: all",
59
+ "type": "acc",
60
+ "value": 26.04
61
+ },
62
+ {
63
+ "slice": "dataset: truthful_qa, split: validation, config: multiple_choice",
64
+ "type": "mc2",
65
+ "value": 37.32
66
+ },
67
+ {
68
+ "slice": "dataset: winogrande, split: validation, config: winogrande_xl",
69
+ "type": "acc",
70
+ "value": 59.51
71
+ },
72
+ {
73
+ "slice": "dataset: gsm8k, split: test, config: main",
74
+ "type": "acc",
75
+ "value": 1.44
76
+ }
77
+ ]
78
+ }
79
+ },
80
+ "name": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
81
+ "authors": [
82
+ {
83
+ "name": "TinyLlama"
84
+ }
85
+ ],
86
+ "tags": [
87
+ "transformers",
88
+ "pytorch",
89
+ "safetensors",
90
+ "llama",
91
+ "text-generation",
92
+ "en",
93
+ "dataset:cerebras/SlimPajama-627B",
94
+ "dataset:bigcode/starcoderdata",
95
+ "license:apache-2.0",
96
+ "model-index",
97
+ "autotrain_compatible",
98
+ "text-generation-inference",
99
+ "endpoints_compatible",
100
+ "region:us"
101
+ ]
102
+ }
103
+ },
104
+ "components": [
105
+ {
106
+ "type": "data",
107
+ "bom-ref": "cerebras/SlimPajama-627B-b36a2f54-050e-55dd-bb65-57b90579dbe6",
108
+ "name": "cerebras/SlimPajama-627B",
109
+ "data": [
110
+ {
111
+ "type": "dataset",
112
+ "bom-ref": "cerebras/SlimPajama-627B-b36a2f54-050e-55dd-bb65-57b90579dbe6",
113
+ "name": "cerebras/SlimPajama-627B",
114
+ "contents": {
115
+ "url": "https://huggingface.co/datasets/cerebras/SlimPajama-627B",
116
+ "properties": [
117
+ {
118
+ "name": "task_categories",
119
+ "value": "text-generation"
120
+ },
121
+ {
122
+ "name": "language",
123
+ "value": "en"
124
+ },
125
+ {
126
+ "name": "pretty_name",
127
+ "value": "SlimPajama-627B"
128
+ }
129
+ ]
130
+ },
131
+ "description": "The dataset consists of 59166 jsonl files and is ~895GB compressed. It is a cleaned and deduplicated version of Together's RedPajama. \nCheck out our blog post explaining our methods, our code on GitHub, and join the discussion on the Cerebras Discord.\n\n\t\n\t\t\n\t\n\t\n\t\tGetting Started\n\t\n\nYou can download the dataset using Hugging Face datasets:\nfrom datasets import load_dataset\nds = load_dataset(\"cerebras/SlimPajama-627B\")\n\n\n\t\n\t\n\t\n\t\tBackground\n\t\n\nToday we are releasing SlimPajama \u2013 the largest\u2026 See the full description on the dataset page: https://huggingface.co/datasets/cerebras/SlimPajama-627B.",
132
+ "governance": {
133
+ "owners": [
134
+ {
135
+ "organization": {
136
+ "name": "cerebras",
137
+ "url": "https://huggingface.co/cerebras"
138
+ }
139
+ }
140
+ ]
141
+ }
142
+ }
143
+ ]
144
+ },
145
+ {
146
+ "type": "data",
147
+ "bom-ref": "bigcode/starcoderdata-abfd2d2a-390d-56b4-ad9c-c532362d5827",
148
+ "name": "bigcode/starcoderdata",
149
+ "data": [
150
+ {
151
+ "type": "dataset",
152
+ "bom-ref": "bigcode/starcoderdata-abfd2d2a-390d-56b4-ad9c-c532362d5827",
153
+ "name": "bigcode/starcoderdata",
154
+ "contents": {
155
+ "url": "https://huggingface.co/datasets/bigcode/starcoderdata",
156
+ "properties": [
157
+ {
158
+ "name": "task_categories",
159
+ "value": "text-generation"
160
+ },
161
+ {
162
+ "name": "language",
163
+ "value": "code"
164
+ },
165
+ {
166
+ "name": "size_categories",
167
+ "value": "unknown"
168
+ },
169
+ {
170
+ "name": "annotations_creators",
171
+ "value": ""
172
+ },
173
+ {
174
+ "name": "language_creators",
175
+ "value": "crowdsourced, expert-generated"
176
+ },
177
+ {
178
+ "name": "pretty_name",
179
+ "value": "The-Stack"
180
+ },
181
+ {
182
+ "name": "source_datasets",
183
+ "value": ""
184
+ },
185
+ {
186
+ "name": "license",
187
+ "value": "other"
188
+ }
189
+ ]
190
+ },
191
+ "description": "\n\t\n\t\t\n\t\tStarCoder Training Dataset\n\t\n\n\n\t\n\t\t\n\t\tDataset description\n\t\n\nThis is the dataset used for training StarCoder and StarCoderBase. It contains 783GB of code in 86 programming languages, and includes 54GB GitHub Issues + 13GB Jupyter notebooks in scripts and text-code pairs,\nand 32GB of GitHub commits, which is approximately 250 Billion tokens.\n\n\t\n\t\t\n\t\n\t\n\t\tDataset creation\n\t\n\nThe creation and filtering of The Stack is explained in the original dataset, we additionally decontaminate and\u2026 See the full description on the dataset page: https://huggingface.co/datasets/bigcode/starcoderdata.",
192
+ "governance": {
193
+ "owners": [
194
+ {
195
+ "organization": {
196
+ "name": "bigcode",
197
+ "url": "https://huggingface.co/bigcode"
198
+ }
199
+ }
200
+ ]
201
+ }
202
+ }
203
+ ]
204
+ }
205
+ ]
206
+ }