Hugging Face's logo

Tiiny
/
SmallThinker-3B-Preview

Text Generation
Transformers
Safetensors
English
qwen2
conversational
text-generation-inference
Model card Files
xet
Community
12

add AIBOM

#12
by RiccardoDav - opened
base: refs/heads/main
←
from: refs/pr/12
Discussion Files changed
+142
-0
Files changed (1) hide show
  1. PowerInfer_SmallThinker-3B-Preview.json +142 -0
PowerInfer_SmallThinker-3B-Preview.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bomFormat": "CycloneDX",
3
+ "specVersion": "1.6",
4
+ "serialNumber": "urn:uuid:0512d493-d5d9-4eee-9d08-d4ee269ab76b",
5
+ "version": 1,
6
+ "metadata": {
7
+ "timestamp": "2025-10-23T16:22:45.078679+00:00",
8
+ "component": {
9
+ "type": "machine-learning-model",
10
+ "bom-ref": "PowerInfer/SmallThinker-3B-Preview-68e7039d-e942-548b-99a3-b3257eaff779",
11
+ "licenses": [],
12
+ "externalReferences": [
13
+ {
14
+ "url": "https://huggingface.co/PowerInfer/SmallThinker-3B-Preview",
15
+ "type": "documentation"
16
+ }
17
+ ],
18
+ "modelCard": {
19
+ "modelParameters": {
20
+ "datasets": [
21
+ {
22
+ "ref": "PowerInfer/QWQ-LONGCOT-500K-522eeed6-5124-53e2-8fac-506db34e4b52"
23
+ },
24
+ {
25
+ "ref": "PowerInfer/LONGCOT-Refine-500K-f17c3140-526e-54e5-8972-3ed05aa3548d"
26
+ }
27
+ ],
28
+ "task": "text-generation",
29
+ "architectureFamily": "qwen2",
30
+ "modelArchitecture": "Qwen2ForCausalLM"
31
+ },
32
+ "properties": [
33
+ {
34
+ "name": "library_name",
35
+ "value": "transformers"
36
+ },
37
+ {
38
+ "name": "base_model",
39
+ "value": "Qwen/Qwen2.5-3B-Instruct"
40
+ }
41
+ ]
42
+ },
43
+ "name": "PowerInfer/SmallThinker-3B-Preview",
44
+ "authors": [
45
+ {
46
+ "name": "PowerInfer"
47
+ }
48
+ ],
49
+ "description": "### model\nmodel_name_or_path: /home/syx/Qwen2.5-3B-Instruct\n",
50
+ "tags": [
51
+ "transformers",
52
+ "safetensors",
53
+ "qwen2",
54
+ "text-generation",
55
+ "conversational",
56
+ "en",
57
+ "dataset:PowerInfer/QWQ-LONGCOT-500K",
58
+ "dataset:PowerInfer/LONGCOT-Refine-500K",
59
+ "base_model:Qwen/Qwen2.5-3B-Instruct",
60
+ "base_model:finetune:Qwen/Qwen2.5-3B-Instruct",
61
+ "autotrain_compatible",
62
+ "text-generation-inference",
63
+ "endpoints_compatible",
64
+ "region:us"
65
+ ]
66
+ }
67
+ },
68
+ "components": [
69
+ {
70
+ "type": "data",
71
+ "bom-ref": "PowerInfer/QWQ-LONGCOT-500K-522eeed6-5124-53e2-8fac-506db34e4b52",
72
+ "name": "PowerInfer/QWQ-LONGCOT-500K",
73
+ "data": [
74
+ {
75
+ "type": "dataset",
76
+ "bom-ref": "PowerInfer/QWQ-LONGCOT-500K-522eeed6-5124-53e2-8fac-506db34e4b52",
77
+ "name": "PowerInfer/QWQ-LONGCOT-500K",
78
+ "contents": {
79
+ "url": "https://huggingface.co/datasets/PowerInfer/QWQ-LONGCOT-500K",
80
+ "properties": [
81
+ {
82
+ "name": "language",
83
+ "value": "en"
84
+ },
85
+ {
86
+ "name": "license",
87
+ "value": "apache-2.0"
88
+ }
89
+ ]
90
+ },
91
+ "description": "This repository contains approximately 500,000 instances of responses generated using QwQ-32B-Preview language model. The dataset combines prompts from multiple high-quality sources to create diverse and comprehensive training data.\nThe dataset is available under the Apache 2.0 license.\nOver 75% of the responses exceed 8,000 tokens in length. The majority of prompts were carefully created using persona-based methods to create challenging instructions.\n\n\t\n\t\t\n\t\n\t\n\t\tBias, Risks, and Limitations\u2026 See the full description on the dataset page: https://huggingface.co/datasets/PowerInfer/QWQ-LONGCOT-500K.",
92
+ "governance": {
93
+ "owners": [
94
+ {
95
+ "organization": {
96
+ "name": "PowerInfer",
97
+ "url": "https://huggingface.co/PowerInfer"
98
+ }
99
+ }
100
+ ]
101
+ }
102
+ }
103
+ ]
104
+ },
105
+ {
106
+ "type": "data",
107
+ "bom-ref": "PowerInfer/LONGCOT-Refine-500K-f17c3140-526e-54e5-8972-3ed05aa3548d",
108
+ "name": "PowerInfer/LONGCOT-Refine-500K",
109
+ "data": [
110
+ {
111
+ "type": "dataset",
112
+ "bom-ref": "PowerInfer/LONGCOT-Refine-500K-f17c3140-526e-54e5-8972-3ed05aa3548d",
113
+ "name": "PowerInfer/LONGCOT-Refine-500K",
114
+ "contents": {
115
+ "url": "https://huggingface.co/datasets/PowerInfer/LONGCOT-Refine-500K",
116
+ "properties": [
117
+ {
118
+ "name": "language",
119
+ "value": "en"
120
+ },
121
+ {
122
+ "name": "license",
123
+ "value": "apache-2.0"
124
+ }
125
+ ]
126
+ },
127
+ "description": "This repository contains approximately 500,000 instances of responses generated using Qwen2.5-72B-Instruct. The dataset combines prompts from multiple high-quality sources to create diverse and comprehensive training data.\nThe dataset is available under the Apache 2.0 license.\n\n\t\n\t\t\n\t\tBias, Risks, and Limitations\n\t\n\n\nThis dataset is mainly in English.\n\nThe dataset inherits the biases, errors, and omissions known to exist in data used for seed sources and models used for data generation.\n\nThis\u2026 See the full description on the dataset page: https://huggingface.co/datasets/PowerInfer/LONGCOT-Refine-500K.",
128
+ "governance": {
129
+ "owners": [
130
+ {
131
+ "organization": {
132
+ "name": "PowerInfer",
133
+ "url": "https://huggingface.co/PowerInfer"
134
+ }
135
+ }
136
+ ]
137
+ }
138
+ }
139
+ ]
140
+ }
141
+ ]
142
+ }