File size: 9,515 Bytes
76ef03a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f992595
0cb6957
f992595
 
76ef03a
 
ad6f1ab
76ef03a
ad6f1ab
76ef03a
82691b0
 
ad6f1ab
76ef03a
82691b0
ad6f1ab
 
76ef03a
 
 
ad6f1ab
76ef03a
ad6f1ab
76ef03a
 
 
 
 
 
 
 
 
 
ad6f1ab
76ef03a
82691b0
76ef03a
3e6eaab
76ef03a
 
 
 
 
 
 
 
 
 
 
3e6eaab
76ef03a
82691b0
76ef03a
3e6eaab
76ef03a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3e6eaab
76ef03a
82691b0
76ef03a
3e6eaab
76ef03a
 
 
 
 
 
 
 
 
3e6eaab
 
 
 
76ef03a
 
3e6eaab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76ef03a
 
 
 
 
 
3e6eaab
76ef03a
 
 
 
 
 
 
 
 
 
 
 
 
de86315
 
ad6f1ab
76ef03a
ad6f1ab
76ef03a
5c9e6a3
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
---
base_model: alpindale/Mistral-7B-v0.2-hf
language:
- en
license: apache-2.0
datasets:
- cognitivecomputations/dolphin
- cognitivecomputations/dolphin-coder
- cognitivecomputations/samantha-data
- jondurbin/airoboros-2.2.1
- teknium/openhermes-2.5
- m-a-p/Code-Feedback
- m-a-p/CodeFeedback-Filtered-Instruction
model-index:
- name: dolphin-2.8-mistral-7b-v02
  results:
  - task:
      type: text-generation
    dataset:
      type: openai_humaneval
      name: HumanEval
    metrics:
    - name: pass@1
      type: pass@1
      value: 0.469
      verified: false
quantized_by: bartowski
pipeline_tag: text-generation
lm_studio:
  param_count: 7b
  use_case: general
  release_date: 28-03-2024
  model_creator: cognitivecomputations
  prompt_template: ChatML
  system_prompt: You are Dolphin, a helpful AI assistant.
  base_model: mistral
  original_repo: cognitivecomputations/dolphin-2.8-mistral-7b-v02
---

## 💫 Community Model> Dolphin 2.8 Mistral 7b v0.2 🐬 by Cognitive Computations

*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.

**Model creator:** [Cognitive Computations](https://huggingface.co/cognitivecomputations)<br>
**Original model**: [dolphin-2.8-mistral-7b-v02](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02)<br>
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b2536](https://github.com/ggerganov/llama.cpp/releases/tag/b2536)<br>

## Model Summary: 
Dolphin 2.8 is a model from from the Dolphin family, based on Mistral 0.2, and fine tuned by [Eric Hartford](https://huggingface.co/ehartford/) and [Cognitive Computations](https://huggingface.co/cognitivecomputations).
With a broad range of uses, this model makes for a great general-use daily driver.<br>

## Prompt Template:

Choose the `ChatML` preset in your LM Studio.

Under the hood, the model will see a prompt that's formatted like so:
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```

## Use case and examples

Dolphin is trained on a vast variety of data, including conversational, logical, and coding. This unique blend, along with a keen eye from the model creators, makes for a wonderful model that can tackle any task you throw at it.

### General knowledge:

```
<|im_start|>system
You are Dolphin, a helpful AI assistant.
<|im_end|>
<|im_start|>user
What does the ISO number mean in camera terminology?<|im_end|>
<|im_start|>assistant
The ISO number in camera terminology refers to the camera's sensitivity to light. ISO stands for International Organization for Standardization. It is a measure of the luminous flux received by a sensor or film.

A higher ISO number means that the camera's sensor is more sensitive to light, allowing for faster shutter speeds in low-light situations. However, increasing the ISO also increases the risk of image noise (graininess) in the final image. Conversely, a lower ISO number means that the camera's sensor is less sensitive to light, requiring slower shutter speeds in well-lit conditions to avoid overexposure.

In summary, the ISO number in camera terminology determines how sensitive the camera's sensor is to light, and it can be adjusted to balance exposure and image quality in various lighting conditions.
```

### Conversational:

```
<|im_start|>system
You are Dolphin, a helpful AI assistant.
<|im_end|>
<|im_start|>user
What is the meaning of life, and how can I find my purpose?<|im_end|>
<|im_start|>assistant
The meaning of life is a subjective and philosophical question that has been debated for centuries. Different people have different perspectives on what gives life meaning, as it can vary greatly from person to person. Some people find meaning in their relationships, their work, or their spiritual beliefs.

To find your purpose, you can follow these steps:

1. Reflect on your passions and interests: Think about the things that genuinely excite you and make you feel alive. Consider what activities you enjoy and what subjects you find most interesting.

2. Explore your talents and strengths: Identify the skills and abilities you possess. You may have natural talents that you can develop and use to contribute to society.

3. Assess your values and principles: Reflect on your beliefs, moral compass, and personal code of conduct. Consider how your values can guide you in determining your purpose.

4. Set goals and objectives: Establish short-term and long-term goals that align with your passions, talents, and values. This will help you stay focused and motivated in your journey to find your purpose.

5. Take action and learn from experience: Begin to pursue the goals and objectives you've set, and learn from the experiences you encounter along the way. Embrace the process of self-discovery and growth.

6. Seek guidance and support: Share your journey with friends, family, or mentors who can offer valuable advice, encouragement, and resources to help you find your purpose.

Ultimately, finding your purpose is a personal and ongoing process that requires introspection, self-awareness, and a willingness to explore new opportunities. Remember, there is no one-size-fits-all answer to the meaning of life, and your purpose may change and evolve over time.
```

### Coding:

```
<|im_start|>system
You are Dolphin, a helpful AI assistant.
<|im_end|>
<|im_start|>user
I have a multi select component in react, and I register it to a useForm. I want to validate that there are no more than 10 items selected on submission. Is this possible?<|im_end|>
<|im_start|>assistant
Yes, it is possible to validate the number of selected items in a multi select component in React with the help of `useForm`. You can use the `validate` function from `react-hook-form` to achieve this. Here's a step-by-step guide on how to do it:

First, import the necessary libraries:
    
    import { useForm } from 'react-hook-form';
    import { MultiSelect } from 'your-multi-select-component';


Next, create a form with the multi select component:

    function MyForm() {
      const { register, handleSubmit, errors } = useForm();
    
      const onSubmit = data => {
       // Handle form submission logic here
      };
    
      return (
      <form onSubmit={handleSubmit(onSubmit)}>
         <MultiSelect
          name="multiSelect"
           ref={register({ required: true, validate: value => value.length <= 10 })}
         />
         {errors.multiSelect && (
           <p>Please select no more than 10 items.</p>
         )}
         <input type="submit" />
       </form>
      );
    }


In the above code, we register the multi select component with the `useForm` hook. The `validate` function is used to validate that the number of selected items is less than or equal to 10. If the validation fails, an error message will be displayed.

Remember to replace `'your-multi-select-component'` with the name of your multi select component.

That's it! Now, when the form is submitted, it will validate that no more than 10 items are selected in the multi select component.
```

## Technical Details

This model was trained with the following datasets:

- [cognitivecomputations/dolphin](https://huggingface.co/datasets/cognitivecomputations/dolphin)
- [cognitivecomputations/dolphin-coder](https://huggingface.co/datasets/cognitivecomputations/dolphin-coder)
- [cognitivecomputations/samantha-data](https://huggingface.co/datasets/cognitivecomputations/samantha-data)
- [jondurbin/airoboros-2.2.1](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1)
- [teknium/openhermes-2.5](https://huggingface.co/datasets/teknium/openhermes-2.5)
- [m-a-p/Code-Feedback](https://huggingface.co/datasets/m-a-p/Code-Feedback)
- [m-a-p/CodeFeedback-Filtered-Instruction](https://huggingface.co/datasets/m-a-p/CodeFeedback-Filtered-Instruction)

## Special thanks

🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.

## Disclaimers

LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model.  You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models.  LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.