aashish1904 commited on
Commit
c6b0139
·
verified ·
1 Parent(s): be6dcfe

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +179 -0
README.md ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+
4
+ language:
5
+ - en
6
+ - zh
7
+ license: apache-2.0
8
+ library_name: transformers
9
+ tags:
10
+ - chat
11
+ - conversational
12
+ - custom-research
13
+ - rp
14
+ - roleplay
15
+ - tool-use
16
+ base_model:
17
+ - Qwen/Qwen2.5-14B-Instruct
18
+ pipeline_tag: text-generation
19
+ model-index:
20
+ - name: miscii-14b-1028
21
+ results:
22
+ - task:
23
+ type: text-generation
24
+ name: Text Generation
25
+ dataset:
26
+ name: IFEval (0-Shot)
27
+ type: HuggingFaceH4/ifeval
28
+ args:
29
+ num_few_shot: 0
30
+ metrics:
31
+ - type: inst_level_strict_acc and prompt_level_strict_acc
32
+ value: 82.37
33
+ name: strict accuracy
34
+ source:
35
+ url: >-
36
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
37
+ name: Open LLM Leaderboard
38
+ - task:
39
+ type: text-generation
40
+ name: Text Generation
41
+ dataset:
42
+ name: BBH (3-Shot)
43
+ type: BBH
44
+ args:
45
+ num_few_shot: 3
46
+ metrics:
47
+ - type: acc_norm
48
+ value: 49.26
49
+ name: normalized accuracy
50
+ source:
51
+ url: >-
52
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
53
+ name: Open LLM Leaderboard
54
+ - task:
55
+ type: text-generation
56
+ name: Text Generation
57
+ dataset:
58
+ name: MATH Lvl 5 (4-Shot)
59
+ type: hendrycks/competition_math
60
+ args:
61
+ num_few_shot: 4
62
+ metrics:
63
+ - type: exact_match
64
+ value: 6.34
65
+ name: exact match
66
+ source:
67
+ url: >-
68
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
69
+ name: Open LLM Leaderboard
70
+ - task:
71
+ type: text-generation
72
+ name: Text Generation
73
+ dataset:
74
+ name: GPQA (0-shot)
75
+ type: Idavidrein/gpqa
76
+ args:
77
+ num_few_shot: 0
78
+ metrics:
79
+ - type: acc_norm
80
+ value: 14.21
81
+ name: acc_norm
82
+ source:
83
+ url: >-
84
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
85
+ name: Open LLM Leaderboard
86
+ - task:
87
+ type: text-generation
88
+ name: Text Generation
89
+ dataset:
90
+ name: MuSR (0-shot)
91
+ type: TAUR-Lab/MuSR
92
+ args:
93
+ num_few_shot: 0
94
+ metrics:
95
+ - type: acc_norm
96
+ value: 12
97
+ name: acc_norm
98
+ source:
99
+ url: >-
100
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
101
+ name: Open LLM Leaderboard
102
+ - task:
103
+ type: text-generation
104
+ name: Text Generation
105
+ dataset:
106
+ name: MMLU-PRO (5-shot)
107
+ type: TIGER-Lab/MMLU-Pro
108
+ config: main
109
+ split: test
110
+ args:
111
+ num_few_shot: 5
112
+ metrics:
113
+ - type: acc
114
+ value: 46.14
115
+ name: accuracy
116
+ source:
117
+ url: >-
118
+ https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sthenno-com/miscii-14b-1028
119
+ name: Open LLM Leaderboard
120
+ datasets:
121
+ - nvidia/HelpSteer2
122
+ - google/Synthetic-Persona-Chat
123
+ - mlabonne/orpo-dpo-mix-40k
124
+
125
+ ---
126
+
127
+ [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
128
+
129
+
130
+ # QuantFactory/miscii-14b-1028-GGUF
131
+ This is quantized version of [sthenno-com/miscii-14b-1028](https://huggingface.co/sthenno-com/miscii-14b-1028) created using llama.cpp
132
+
133
+ # Original Model Card
134
+
135
+
136
+ # miscii-14b-1028
137
+
138
+ ## Role-based Instructions
139
+
140
+ Just parse the following as your system prompt.
141
+ Note there is NO `special-tokens` here.
142
+
143
+ ```python
144
+ system_prompt: str = (
145
+ """<|context_start|>personas
146
+ <|user_persona_start|>statement
147
+ {user_persona}<|user_persona_end|>
148
+ <|assistant_persona_start|>statement
149
+ {assistant_persona}<|assistant_persona_end|><|context_end|>""".format(
150
+ user_persona="""I am Miscii. # example
151
+ <optional: personal statement, e.g. I am the designer of Sthenno.>
152
+ <optional: additional statements>""",
153
+ assistant_persona="""I am Sthenno. # example
154
+ <optional: personal statement, e.g. I speak in Chinese.>
155
+ <optional: additional statements>""",
156
+ )
157
+ )
158
+ ```
159
+
160
+ ## Training
161
+
162
+ See [Report for miscii-1020](https://api.wandb.ai/links/flandrelabs-carnegie-mellon-university/p35vchzx) for more details.
163
+
164
+ -----
165
+
166
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
167
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sthenno-com__miscii-14b-1028)
168
+
169
+ | Metric |Value|
170
+ |-------------------|----:|
171
+ |Avg. |35.05|
172
+ |IFEval (0-Shot) |82.37|
173
+ |BBH (3-Shot) |49.26|
174
+ |MATH Lvl 5 (4-Shot)| 6.34|
175
+ |GPQA (0-shot) |14.21|
176
+ |MuSR (0-shot) |12.00|
177
+ |MMLU-PRO (5-shot) |46.14|
178
+
179
+ $$\large{\text{There's nothing more to Show}}$$