bartowski commited on
Commit
76ef03a
0 Parent(s):

Duplicate from lmstudio-ai/dolphin-2.8-mistral-7b-v02-GGUF

Browse files
.gitattributes ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ dolphin-2.8-mistral-7b-v02-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ dolphin-2.8-mistral-7b-v02-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ dolphin-2.8-mistral-7b-v02-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
39
+ dolphin-2.8-mistral-7b-v02-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
40
+ dolphin-2.8-mistral-7b-v02-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
41
+ dolphin-2.8-mistral-7b-v02-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
42
+ dolphin-2.8-mistral-7b-v02-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ dolphin-2.8-mistral-7b-v02-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ dolphin-2.8-mistral-7b-v02-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
45
+ dolphin-2.8-mistral-7b-v02-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ dolphin-2.8-mistral-7b-v02-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ dolphin-2.8-mistral-7b-v02-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ dolphin-2.8-mistral-7b-v02-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ dolphin-2.8-mistral-7b-v02-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ dolphin-2.8-mistral-7b-v02-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ dolphin-2.8-mistral-7b-v02-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: alpindale/Mistral-7B-v0.2-hf
3
+ language:
4
+ - en
5
+ license: apache-2.0
6
+ datasets:
7
+ - cognitivecomputations/dolphin
8
+ - cognitivecomputations/dolphin-coder
9
+ - cognitivecomputations/samantha-data
10
+ - jondurbin/airoboros-2.2.1
11
+ - teknium/openhermes-2.5
12
+ - m-a-p/Code-Feedback
13
+ - m-a-p/CodeFeedback-Filtered-Instruction
14
+ model-index:
15
+ - name: dolphin-2.8-mistral-7b-v02
16
+ results:
17
+ - task:
18
+ type: text-generation
19
+ dataset:
20
+ type: openai_humaneval
21
+ name: HumanEval
22
+ metrics:
23
+ - name: pass@1
24
+ type: pass@1
25
+ value: 0.469
26
+ verified: false
27
+ quantized_by: bartowski
28
+ pipeline_tag: text-generation
29
+ lm_studio:
30
+ param_count: 7b
31
+ use_case: general
32
+ release_date: 28-03-2024
33
+ model_creator: cognitivecomputations
34
+ ---
35
+
36
+ ## Dolphin 2.8 Mistral 7b v0.2 🐬 by Cognitive Computations
37
+
38
+ Special thanks to [Cognitive Computations](https://huggingface.co/cognitivecomputations) for providing this model!
39
+
40
+ Dolphin 2.8 is a model from from the Dolphin family, based on Mistral 0.2, and fine tuned by Eric Hartford and Cognitive Computations. With a broad range of uses, this model makes for a great general-use daily driver.
41
+
42
+ Original model can be found [here](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02)
43
+
44
+ ## Prompt Template:
45
+
46
+ This model uses ChatML as follows:
47
+
48
+ ```
49
+ <|im_start|>system
50
+ You are Dolphin, a helpful AI assistant.<|im_end|>
51
+ <|im_start|>user
52
+ {prompt}<|im_end|>
53
+ <|im_start|>assistant
54
+
55
+ ```
56
+
57
+ ## Use case and examples
58
+
59
+ Dolphin is trained on a huge 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!
60
+
61
+ General knowledge:
62
+
63
+ ```
64
+ <|im_start|>system
65
+ You are Dolphin, a helpful AI assistant.
66
+ <|im_end|>
67
+ <|im_start|>user
68
+ What does the ISO number mean in camera terminology?<|im_end|>
69
+ <|im_start|>assistant
70
+ 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.
71
+
72
+ 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.
73
+
74
+ 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.
75
+ ```
76
+
77
+ Conversational:
78
+
79
+ ```
80
+ <|im_start|>system
81
+ You are Dolphin, a helpful AI assistant.
82
+ <|im_end|>
83
+ <|im_start|>user
84
+ What is the meaning of life, and how can I find my purpose?<|im_end|>
85
+ <|im_start|>assistant
86
+ 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.
87
+
88
+ To find your purpose, you can follow these steps:
89
+
90
+ 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.
91
+
92
+ 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.
93
+
94
+ 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.
95
+
96
+ 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.
97
+
98
+ 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.
99
+
100
+ 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.
101
+
102
+ 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.
103
+ ```
104
+
105
+ Coding:
106
+
107
+ ```
108
+ <|im_start|>system
109
+ You are Dolphin, a helpful AI assistant.
110
+ <|im_end|>
111
+ <|im_start|>user
112
+ 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|>
113
+ <|im_start|>assistant
114
+ 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:
115
+
116
+ First, import the necessary libraries:
117
+ ```jsx
118
+ import { useForm } from 'react-hook-form';
119
+ import { MultiSelect } from 'your-multi-select-component';
120
+ ```
121
+
122
+ Next, create a form with the multi select component:
123
+ ```jsx
124
+ function MyForm() {
125
+ const { register, handleSubmit, errors } = useForm();
126
+
127
+ const onSubmit = data => {
128
+ // Handle form submission logic here
129
+ };
130
+
131
+ return (
132
+ <form onSubmit={handleSubmit(onSubmit)}>
133
+ <MultiSelect
134
+ name="multiSelect"
135
+ ref={register({ required: true, validate: value => value.length <= 10 })}
136
+ />
137
+ {errors.multiSelect && (
138
+ <p>Please select no more than 10 items.</p>
139
+ )}
140
+ <input type="submit" />
141
+ </form>
142
+ );
143
+ }
144
+ ```
145
+
146
+ 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.
147
+
148
+ Remember to replace `'your-multi-select-component'` with the name of your multi select component.
149
+
150
+ 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.
151
+ ```
152
+
153
+ ## Technical Details
154
+
155
+ This model was trained with the following datasets:
156
+
157
+ - [cognitivecomputations/dolphin](https://huggingface.co/datasets/cognitivecomputations/dolphin)
158
+ - [cognitivecomputations/dolphin-coder](https://huggingface.co/datasets/cognitivecomputations/dolphin-coder)
159
+ - [cognitivecomputations/samantha-data](https://huggingface.co/datasets/cognitivecomputations/samantha-data)
160
+ - [jondurbin/airoboros-2.2.1](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1)
161
+ - [teknium/openhermes-2.5](https://huggingface.co/datasets/teknium/openhermes-2.5)
162
+ - [m-a-p/Code-Feedback](https://huggingface.co/datasets/m-a-p/Code-Feedback)
163
+ - [m-a-p/CodeFeedback-Filtered-Instruction](https://huggingface.co/datasets/m-a-p/CodeFeedback-Filtered-Instruction)
164
+
165
+ GGUF files provided by [bartowski](https://huggingface.co/bartowski) based on release [b2536](https://github.com/ggerganov/llama.cpp/releases/tag/b2536)
166
+
167
+ Special thanks to Georgi Gerganov and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible
168
+
169
+ ## Legal Disclaimers
170
+
171
+ TODO: Insert here
dolphin-2.8-mistral-7b-v02-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f55e37c371b25266fd9d06d3f2504a66742c35c843ec4f7bfa5c4a833ace6eb
3
+ size 3284901952
dolphin-2.8-mistral-7b-v02-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf5cc4eb6689acb5b609750443af6066461f20302be89551e6361f4f48a8d2ab
3
+ size 3182403648
dolphin-2.8-mistral-7b-v02-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:396b28d5ba48da0a4d4d3d564b1793c8c0721b404ec3bde2cbed9f0944370c10
3
+ size 4155065472
dolphin-2.8-mistral-7b-v02-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef64d88e5a6461d0705f7cc436cfd19dd3305ee5310ea5091f2716af6706d435
3
+ size 3944399744
dolphin-2.8-mistral-7b-v02-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47973d42442cda21d9acd66fdc0231ff4698a0982346d83681967dd5c39c9a72
3
+ size 2719251712
dolphin-2.8-mistral-7b-v02-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a16b72d1962f9b6702f85dffa45a110ee1c12d5e3cb297de43701e422b536d4a
3
+ size 3822035008
dolphin-2.8-mistral-7b-v02-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06f1917ccca147f426fd5810f975829cf9822170c607a13003bbf28e8aaf5ccf
3
+ size 3518996544
dolphin-2.8-mistral-7b-v02-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d8f60d8f50190d3ef0085c0ced9fabe04bd5c8c18b3840e48f640100c5dbbf
3
+ size 3164577856
dolphin-2.8-mistral-7b-v02-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7eb0add3f5bde0d4f35e878d1fe8f547fb5d909035d76b66c0e87c30163785c
3
+ size 4108928128
dolphin-2.8-mistral-7b-v02-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acf5681de049fe3c2486def0e744089b6d1894cf613700386c9d5c17a3a07412
3
+ size 4368450688
dolphin-2.8-mistral-7b-v02-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b9796ca246ef8bd0a2409a662592be63e687597e0988e9444b14f879c7682b
3
+ size 4140385408
dolphin-2.8-mistral-7b-v02-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a0142ed0da77ad5ffb53e5429c92992c6b88c4ea2d1e146372282dbe3b1e946
3
+ size 4997728384
dolphin-2.8-mistral-7b-v02-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063751ffeadf1e692432e7b1b288e51fb32db0bde86abc09f26850ab05a50f92
3
+ size 5131421824
dolphin-2.8-mistral-7b-v02-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:974647f39d67f422186d520f036b665b46e082e1632e131cf6aabd363a1e9c78
3
+ size 4997728384
dolphin-2.8-mistral-7b-v02-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40037a7b7796f8d97270d96570531a32d6197f22dd8c37a60ba5fe84ef415276
3
+ size 5942078656
dolphin-2.8-mistral-7b-v02-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60b64563d5e4e78211eb3dfb1af75c3c89d1158f141bc0bf38ec5eac30fbb
3
+ size 7695875136
original_repo_url.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF