Hugging Face's logo

bartowski
/
Llama3.2-3B-ShiningValiant2-GGUF

Text Generation
GGUF
English
shining-valiant
shining-valiant-2
valiant
valiant-labs
llama
llama-3.2
llama-3.2-instruct
llama-3.2-instruct-3b
llama-3
llama-3-instruct
llama-3-instruct-3b
3b
science
physics
biology
chemistry
compsci
computer-science
engineering
technical
conversational
chat
instruct
Eval Results
Inference Endpoints
Model card Files Community
bartowski commited on
Commit
8129a56
•
1 Parent(s): c48e1cd

Update metadata with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +188 -1
README.md CHANGED
@@ -1,6 +1,193 @@
1
  ---
2
- quantized_by: bartowski
 
 
 
 
 
 
3
  pipeline_tag: text-generation
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ---
5
 
6
  ## Llamacpp imatrix Quantizations of Llama3.2-3B-ShiningValiant2
 
1
  ---
2
+ base_model: ValiantLabs/Llama3.2-3B-ShiningValiant2
3
+ datasets:
4
+ - sequelbox/Celestia
5
+ - sequelbox/Supernova
6
+ language:
7
+ - en
8
+ license: llama3.2
9
  pipeline_tag: text-generation
10
+ tags:
11
+ - shining-valiant
12
+ - shining-valiant-2
13
+ - valiant
14
+ - valiant-labs
15
+ - llama
16
+ - llama-3.2
17
+ - llama-3.2-instruct
18
+ - llama-3.2-instruct-3b
19
+ - llama-3
20
+ - llama-3-instruct
21
+ - llama-3-instruct-3b
22
+ - 3b
23
+ - science
24
+ - physics
25
+ - biology
26
+ - chemistry
27
+ - compsci
28
+ - computer-science
29
+ - engineering
30
+ - technical
31
+ - conversational
32
+ - chat
33
+ - instruct
34
+ quantized_by: bartowski
35
+ model_type: llama
36
+ model-index:
37
+ - name: Llama3.2-3B-ShiningValiant2
38
+ results:
39
+ - task:
40
+ type: text-generation
41
+ name: Text Generation
42
+ dataset:
43
+ name: Winogrande (5-shot)
44
+ type: winogrande
45
+ args:
46
+ num_few_shot: 5
47
+ metrics:
48
+ - type: acc
49
+ value: 69.85
50
+ name: acc
51
+ - task:
52
+ type: text-generation
53
+ name: Text Generation
54
+ dataset:
55
+ name: ARC Challenge (25-Shot)
56
+ type: arc_challenge
57
+ args:
58
+ num_few_shot: 25
59
+ metrics:
60
+ - type: acc_norm
61
+ value: 46.25
62
+ name: normalized accuracy
63
+ - task:
64
+ type: text-generation
65
+ name: Text Generation
66
+ dataset:
67
+ name: MMLU College Biology (5-shot)
68
+ type: mmlu
69
+ args:
70
+ num_few_shot: 5
71
+ metrics:
72
+ - type: acc
73
+ value: 56.25
74
+ name: acc
75
+ - type: acc
76
+ value: 63.55
77
+ name: acc
78
+ - type: acc
79
+ value: 41.0
80
+ name: acc
81
+ - type: acc
82
+ value: 41.38
83
+ name: acc
84
+ - type: acc
85
+ value: 34.31
86
+ name: acc
87
+ - type: acc
88
+ value: 35.76
89
+ name: acc
90
+ - type: acc
91
+ value: 48.0
92
+ name: acc
93
+ - type: acc
94
+ value: 58.0
95
+ name: acc
96
+ - type: acc
97
+ value: 45.54
98
+ name: acc
99
+ - task:
100
+ type: text-generation
101
+ name: Text Generation
102
+ dataset:
103
+ name: IFEval (0-Shot)
104
+ type: HuggingFaceH4/ifeval
105
+ args:
106
+ num_few_shot: 0
107
+ metrics:
108
+ - type: inst_level_strict_acc and prompt_level_strict_acc
109
+ value: 48.9
110
+ name: strict accuracy
111
+ source:
112
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
113
+ name: Open LLM Leaderboard
114
+ - task:
115
+ type: text-generation
116
+ name: Text Generation
117
+ dataset:
118
+ name: BBH (3-Shot)
119
+ type: BBH
120
+ args:
121
+ num_few_shot: 3
122
+ metrics:
123
+ - type: acc_norm
124
+ value: 19.11
125
+ name: normalized accuracy
126
+ source:
127
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
128
+ name: Open LLM Leaderboard
129
+ - task:
130
+ type: text-generation
131
+ name: Text Generation
132
+ dataset:
133
+ name: MATH Lvl 5 (4-Shot)
134
+ type: hendrycks/competition_math
135
+ args:
136
+ num_few_shot: 4
137
+ metrics:
138
+ - type: exact_match
139
+ value: 9.14
140
+ name: exact match
141
+ source:
142
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
143
+ name: Open LLM Leaderboard
144
+ - task:
145
+ type: text-generation
146
+ name: Text Generation
147
+ dataset:
148
+ name: GPQA (0-shot)
149
+ type: Idavidrein/gpqa
150
+ args:
151
+ num_few_shot: 0
152
+ metrics:
153
+ - type: acc_norm
154
+ value: 3.02
155
+ name: acc_norm
156
+ source:
157
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
158
+ name: Open LLM Leaderboard
159
+ - task:
160
+ type: text-generation
161
+ name: Text Generation
162
+ dataset:
163
+ name: MuSR (0-shot)
164
+ type: TAUR-Lab/MuSR
165
+ args:
166
+ num_few_shot: 0
167
+ metrics:
168
+ - type: acc_norm
169
+ value: 5.49
170
+ name: acc_norm
171
+ source:
172
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
173
+ name: Open LLM Leaderboard
174
+ - task:
175
+ type: text-generation
176
+ name: Text Generation
177
+ dataset:
178
+ name: MMLU-PRO (5-shot)
179
+ type: TIGER-Lab/MMLU-Pro
180
+ config: main
181
+ split: test
182
+ args:
183
+ num_few_shot: 5
184
+ metrics:
185
+ - type: acc
186
+ value: 19.1
187
+ name: accuracy
188
+ source:
189
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-ShiningValiant2
190
+ name: Open LLM Leaderboard
191
  ---
192
 
193
  ## Llamacpp imatrix Quantizations of Llama3.2-3B-ShiningValiant2