File size: 10,558 Bytes
c87efb6
3f9518b
6c165b5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c87efb6
 
3f9518b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fd221c8
 
 
 
 
 
 
 
a0045a9
 
 
 
3f9518b
c87efb6
3f9518b
 
 
 
 
 
 
 
 
 
 
 
 
 
77b637e
3f9518b
 
 
 
 
 
 
 
6c165b5
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
---
license: llama3
model-index:
- name: llama-3-cat-8b-instruct-v1
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 59.04
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 79.2
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 62.99
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 50.8
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 75.93
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 60.5
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheSkullery/llama-3-cat-8b-instruct-v1
      name: Open LLM Leaderboard
---

<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  <title>Cat-llama3-instruct Data Card</title>
  <link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet">
  <style>
    body {
      font-family: 'Quicksand', sans-serif;
      background: linear-gradient(135deg, #2E3440 0%, #1A202C 100%);
      color: #D8DEE9;
      margin: 0;
      padding: 0;
      font-size: 16px;
    }
    .container {
      width: 80%;
      max-width: 800px;
      margin: 20px auto;
      background-color: rgba(255, 255, 255, 0.02);
      padding: 20px;
      border-radius: 12px;
      box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2);
      backdrop-filter: blur(10px);
      border: 1px solid rgba(255, 255, 255, 0.1);
    }
    .header h1 {
      font-size: 28px;
      color: #ECEFF4;
      margin: 0 0 20px 0;
      text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.3);
    }
    .update-section {
      margin-top: 30px;
    }
    .update-section h2 {
      font-size: 24px;
      color: #88C0D0;
    }
    .update-section p {
      font-size: 16px;
      line-height: 1.6;
      color: #ECEFF4;
    }
    .info img {
      width: 100%;
      border-radius: 10px;
      margin-bottom: 15px;
    }
    a {
      color: #88C0D0;
      text-decoration: none;
    }
    a:hover {
      color: #A3BE8C;
    }
    pre {
      background-color: rgba(255, 255, 255, 0.05);
      padding: 10px;
      border-radius: 5px;
      overflow-x: auto;
    }
    code {
      font-family: 'Courier New', monospace;
      color: #A3BE8C;
    }
  </style>
</head>
<body>
  <div class="container">
    <div class="header">
      <h1>Cat-llama3-instruct</h1>
    </div>
    <div class="info">
           <img src="https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/Uw0ycicMjZufSFTgXZMFd.png" alt="Model Card">
      <p>Presented by:<p/>
      <ul>
        <li>Dataset Builder: Dr. Kal'tsit (Kat)</li>
        <li>Trainer/Funding: SteelSkull</li>
        <li>Facilitator: Potatooff</li>
      </ul>
      <p><a href="https://huggingface.co/turboderp/Cat-Llama-3-70B-instruct">70b variant of the model</a> (Trained by Dr. Kal'tsit, Posted by Turboderp), Please check it out!</p>
      <h2>About:</h2>
      <p>Cat-llama3-instruct is a llama 3 8b finetuned model focusing on system prompt fidelity, helpfulness and character engagement. The model aims to respect system prompt to an extreme degree, provide helpful information regardless of situations, and offer maximum character immersion (Role Play) in given scenes.</p>
      <h2>Specific Aims:</h2>
      <ul>
        <li>System Instruction fidelity</li>
        <li>Chain of Thought (COT)</li>
        <li>Character immersion</li>
        <li>Helpfulness for biosciences and general science</li>
      </ul>
      <h3>Methods</h3>
      <h4>Dataset Preparation</h4>
      <p>Huggingface dataset containing instruction-response pairs was systematically pulled. A GPT model was trained on high quality and helpful responses exclusively to serve as a standard model.</p>
      <img src="https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/HovhwLIGO9cz8Az-h0tkn.png" alt="Huggingface dataset population distribution and filtration for each component">
      <p>(Fig1. Huggingface dataset population distribution and filtration for each component)</p>
      <p>The dataset was further filtered for length and COT responses:</p>
      <img src="https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/-z9cZDNuGyCftdrZwR_46.png" alt="COT responses">
      <p>(Fig 2. COT responses are all >50 tokens single turn)</p>
      <p>Health-related data was also pulled from Chat Doctor, favoring detailed and step-by-step diagnosis:</p>
      <img src="https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/RnXyoR6wyBDWfIy3vMvWm.png" alt="Health-related tasks">
      <p>(Fig 3. Health related tasks are all >100 tokens, peaking at 450 tokens single turn)</p>
      <h3>Model Training</h3>
      <p>1*a100 for 6 days, 4 epochs</p>
      <h2>Usage:</h2>
      <h3>Prompt format: llama 3 </h3>
      <ul>
        <li>Settings/Context/Instruct (Provided by @Anthonyg5005)</li>
        <li><a href="https://huggingface.co/TheSkullery/llama-3-cat-8b-instruct-v1/raw/main/Cat%208B%20Gen%20Settings.json">Cat 8B Gen Settings</a></li>
        <li><a href="https://huggingface.co/TheSkullery/llama-3-cat-8b-instruct-v1/raw/main/Cat%208b%20Context.json">Cat 8b Context</a></li>
        <li><a href="https://huggingface.co/TheSkullery/llama-3-cat-8b-instruct-v1/raw/main/Cat%208b%20Instruct.json">Cat 8b Instruct</a></li>
      </ul>
      <h3>Quants: </h3>
      <ul>
        <li><a href="https://huggingface.co/bartowski/llama-3-cat-8b-instruct-v1-GGUF">[bartowski/llama-3-cat-8b-instruct-v1-GGUF]</a></li>
      </ul>
      <pre><code> <|begin_of_text|>Below is a conversation between an user and an AI assistant. The ai assistant gives response regarding user's questions. USER: user: Given the task definition and input, reply with output. In this task, you are given a question and an answer, you would be asked to create the sentence based on the Question-Answer provided. It should be contained within the Question-Answer provided.

Question: What type of diseases in humans are caused by protozoa? Answer: protist diseases
ASSISTANT: AI: Task Explanation:
In this task, you are asked to create a sentence using the given question and the provided answer. The sentence you create should include the information from both the question and the answer in a concise and coherent manner.
Guidelines:
1. Read the given question and answer carefully.
2. Combine the information from the question and answer to create a new sentence.
3. Make sure your new sentence contains both the question's information and the answer provided.
4. Check your sentence for proper grammar and punctuation.
Steps to find the answer:
1. Read the question: "What type of diseases in humans are caused by protozoa?"
2. Read the answer: "protist diseases"
3. Combine the information from the question and answer to create a new sentence: "In humans, protist diseases are caused by protozoa."
4. Double-check the sentence for proper grammar and punctuation, and make necessary adjustments if needed.
Final Output:
In humans, protist diseases are caused by protozoa.< / s ><|end_of_text|></code></pre>
      <h2>Showcases:</h2>
      <p>The model does COT in grey, calculated response in black; note that this behaviour is done through system card instruction to showcase the systemcard fidelity, it is not fine tuned into the model.</p>
      <img src="https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/6smLuiePQa8Y2H19ie-ZY.png" alt="Showcase 1">
      <img src="https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/g9oP03RboHBBipk70GIHO.png" alt="Showcase 2">
      <p>(Fig 4. Showcasing model doing COT to solve difficult tasks, extend and enrich its own answers)</p>
    </div>
  </div>
</body>
</html>
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TheSkullery__llama-3-cat-8b-instruct-v1)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |64.74|
|AI2 Reasoning Challenge (25-Shot)|59.04|
|HellaSwag (10-Shot)              |79.20|
|MMLU (5-Shot)                    |62.99|
|TruthfulQA (0-shot)              |50.80|
|Winogrande (5-shot)              |75.93|
|GSM8k (5-shot)                   |60.50|