Hugging Face's logo

RichardErkhov
/
NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf

GGUF
Inference Endpoints
Model card Files Community
RichardErkhov commited on
Commit
9de5186
•
1 Parent(s): 4e2b159

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +179 -0
README.md ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ shark_tank_ai_7b_v2 - GGUF
11
+ - Model creator: https://huggingface.co/NExtNewChattingAI/
12
+ - Original model: https://huggingface.co/NExtNewChattingAI/shark_tank_ai_7b_v2/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [shark_tank_ai_7b_v2.Q2_K.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q2_K.gguf) | Q2_K | 2.53GB |
18
+ | [shark_tank_ai_7b_v2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
19
+ | [shark_tank_ai_7b_v2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.IQ3_S.gguf) | IQ3_S | 2.96GB |
20
+ | [shark_tank_ai_7b_v2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
21
+ | [shark_tank_ai_7b_v2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.IQ3_M.gguf) | IQ3_M | 3.06GB |
22
+ | [shark_tank_ai_7b_v2.Q3_K.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q3_K.gguf) | Q3_K | 3.28GB |
23
+ | [shark_tank_ai_7b_v2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
24
+ | [shark_tank_ai_7b_v2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
25
+ | [shark_tank_ai_7b_v2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
26
+ | [shark_tank_ai_7b_v2.Q4_0.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q4_0.gguf) | Q4_0 | 3.83GB |
27
+ | [shark_tank_ai_7b_v2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
28
+ | [shark_tank_ai_7b_v2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
29
+ | [shark_tank_ai_7b_v2.Q4_K.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q4_K.gguf) | Q4_K | 4.07GB |
30
+ | [shark_tank_ai_7b_v2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
31
+ | [shark_tank_ai_7b_v2.Q4_1.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q4_1.gguf) | Q4_1 | 4.24GB |
32
+ | [shark_tank_ai_7b_v2.Q5_0.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q5_0.gguf) | Q5_0 | 4.65GB |
33
+ | [shark_tank_ai_7b_v2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
34
+ | [shark_tank_ai_7b_v2.Q5_K.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q5_K.gguf) | Q5_K | 4.78GB |
35
+ | [shark_tank_ai_7b_v2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
36
+ | [shark_tank_ai_7b_v2.Q5_1.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q5_1.gguf) | Q5_1 | 5.07GB |
37
+ | [shark_tank_ai_7b_v2.Q6_K.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q6_K.gguf) | Q6_K | 5.53GB |
38
+ | [shark_tank_ai_7b_v2.Q8_0.gguf](https://huggingface.co/RichardErkhov/NExtNewChattingAI_-_shark_tank_ai_7b_v2-gguf/blob/main/shark_tank_ai_7b_v2.Q8_0.gguf) | Q8_0 | 7.17GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ language:
46
+ - en
47
+ license: cc-by-nc-4.0
48
+ model-index:
49
+ - name: shark_tank_ai_7b_v2
50
+ results:
51
+ - task:
52
+ type: text-generation
53
+ name: Text Generation
54
+ dataset:
55
+ name: AI2 Reasoning Challenge (25-Shot)
56
+ type: ai2_arc
57
+ config: ARC-Challenge
58
+ split: test
59
+ args:
60
+ num_few_shot: 25
61
+ metrics:
62
+ - type: acc_norm
63
+ value: 67.75
64
+ name: normalized accuracy
65
+ source:
66
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NExtNewChattingAI/shark_tank_ai_7b_v2
67
+ name: Open LLM Leaderboard
68
+ - task:
69
+ type: text-generation
70
+ name: Text Generation
71
+ dataset:
72
+ name: HellaSwag (10-Shot)
73
+ type: hellaswag
74
+ split: validation
75
+ args:
76
+ num_few_shot: 10
77
+ metrics:
78
+ - type: acc_norm
79
+ value: 87.06
80
+ name: normalized accuracy
81
+ source:
82
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NExtNewChattingAI/shark_tank_ai_7b_v2
83
+ name: Open LLM Leaderboard
84
+ - task:
85
+ type: text-generation
86
+ name: Text Generation
87
+ dataset:
88
+ name: MMLU (5-Shot)
89
+ type: cais/mmlu
90
+ config: all
91
+ split: test
92
+ args:
93
+ num_few_shot: 5
94
+ metrics:
95
+ - type: acc
96
+ value: 58.79
97
+ name: accuracy
98
+ source:
99
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NExtNewChattingAI/shark_tank_ai_7b_v2
100
+ name: Open LLM Leaderboard
101
+ - task:
102
+ type: text-generation
103
+ name: Text Generation
104
+ dataset:
105
+ name: TruthfulQA (0-shot)
106
+ type: truthful_qa
107
+ config: multiple_choice
108
+ split: validation
109
+ args:
110
+ num_few_shot: 0
111
+ metrics:
112
+ - type: mc2
113
+ value: 62.15
114
+ source:
115
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NExtNewChattingAI/shark_tank_ai_7b_v2
116
+ name: Open LLM Leaderboard
117
+ - task:
118
+ type: text-generation
119
+ name: Text Generation
120
+ dataset:
121
+ name: Winogrande (5-shot)
122
+ type: winogrande
123
+ config: winogrande_xl
124
+ split: validation
125
+ args:
126
+ num_few_shot: 5
127
+ metrics:
128
+ - type: acc
129
+ value: 78.45
130
+ name: accuracy
131
+ source:
132
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NExtNewChattingAI/shark_tank_ai_7b_v2
133
+ name: Open LLM Leaderboard
134
+ - task:
135
+ type: text-generation
136
+ name: Text Generation
137
+ dataset:
138
+ name: GSM8k (5-shot)
139
+ type: gsm8k
140
+ config: main
141
+ split: test
142
+ args:
143
+ num_few_shot: 5
144
+ metrics:
145
+ - type: acc
146
+ value: 45.11
147
+ name: accuracy
148
+ source:
149
+ url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NExtNewChattingAI/shark_tank_ai_7b_v2
150
+ name: Open LLM Leaderboard
151
+ ---
152
+ This model is based on https://huggingface.co/AIDC-ai-business/Marcoroni-7B-v3 trained on internal data.
153
+ ---
154
+ license: cc-by-nc-4.0
155
+ language:
156
+ - en
157
+ ---
158
+ Chatbot is a highly advanced artificial intelligence designed to provide you with personalized assistance and support. With its natural language processing capabilities, it can understand and respond to a wide range of queries and requests, making it a valuable tool for both personal and professional use.
159
+
160
+ The chatbot is equipped with a vast knowledge base, allowing it to provide accurate and reliable information on a wide range of topics, from general knowledge to specific industry-related information. It can also perform tasks such as scheduling appointments, sending emails, and even ordering products online.
161
+
162
+ One of the standout features of this assistant chatbot is its ability to learn and adapt to your individual preferences and needs. Over time, it can become more personalized to your specific requirements, making it an even more valuable asset to your daily life.
163
+
164
+ The chatbot is also designed to be user-friendly and intuitive, with a simple and easy-to-use interface that allows you to interact with it in a natural and conversational way. Whether you're looking for information, need help with a task, or just want to chat, your assistant chatbot is always ready and available to assist you.
165
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
166
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NExtNewChattingAI__shark_tank_ai_7b_v2)
167
+
168
+ | Metric |Value|
169
+ |---------------------------------|----:|
170
+ |Avg. |66.55|
171
+ |AI2 Reasoning Challenge (25-Shot)|67.75|
172
+ |HellaSwag (10-Shot) |87.06|
173
+ |MMLU (5-Shot) |58.79|
174
+ |TruthfulQA (0-shot) |62.15|
175
+ |Winogrande (5-shot) |78.45|
176
+ |GSM8k (5-shot) |45.11|
177
+
178
+
179
+