Corianas commited on
Commit
687bb9e
1 Parent(s): 2d1ec9e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +185 -2
README.md CHANGED
@@ -1,7 +1,190 @@
1
  ---
2
- license: apache-2.0
3
  datasets:
 
4
  - guanaco/guanaco
5
  language:
6
  - en
7
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: cc-by-nc-sa-4.0
3
  datasets:
4
+ - the_pile
5
  - guanaco/guanaco
6
  language:
7
  - en
8
+ ---
9
+
10
+ # Model Card for Cerebras 2.7b Dollyfied.
11
+
12
+ This is a finetuned model of Cerebras 2.7b model. using DataBricksLabs Dolly Framework
13
+
14
+ ## Model Details
15
+
16
+ ### Model Description
17
+
18
+ This is a finetuned version of cerebras' 111million paramater model that has been trained to follow instructions.
19
+
20
+ It was accomplished using DataBricks Dolly training tools, and was trained for 2 epochs.
21
+
22
+ - **Developed by:** Finetuned by Corianas (me) using open source tools
23
+ - **Shared by [optional]:** [More Information Needed]
24
+ - **Model type:** [More Information Needed]
25
+ - **Language(s) (NLP):** EN
26
+ - **License:** cc-by-nc-4.0
27
+ - **Finetuned from model:** https://huggingface.co/cerebras/Cerebras-GPT-111m
28
+ - **Finetuned using:** https://www.databricks.com/blog/2023/03/24/hello-dolly-democratizing-magic-chatgpt-open-models.html
29
+
30
+ ## Uses
31
+
32
+ This is a simple GPT chatbot that has been finetuned to understand instructions.
33
+ Its knowledge about facts about the world is should be considered suspect at best.
34
+
35
+ ### Direct Use
36
+
37
+ If you have a use you put it to, Please let me know.
38
+
39
+ [More Information Needed]
40
+
41
+ ### Downstream Use [optional]
42
+
43
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
44
+
45
+ [More Information Needed]
46
+
47
+ ### Out-of-Scope Use
48
+
49
+ Any form of use where any form of accuracy is needed.
50
+ FOR THE LOVE OF GOD DO NOT FOLLOW MEDICAL ADVICE FROM THIS.
51
+ or financial advice.
52
+
53
+ [More Information Needed]
54
+
55
+ ## Bias, Risks, and Limitations
56
+
57
+ Limitations... Yes, I am sure there are so so many.
58
+
59
+ [More Information Needed]
60
+
61
+ ## How to Get Started with the Model
62
+
63
+ Use the code below to get started with the model.
64
+
65
+ [More Information Needed]
66
+
67
+ ## Training Details
68
+
69
+ ### Training Data
70
+
71
+ <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
72
+
73
+ [More Information Needed]
74
+
75
+ ### Training Procedure
76
+
77
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
78
+
79
+ #### Preprocessing [optional]
80
+
81
+ [More Information Needed]
82
+
83
+
84
+ #### Training Hyperparameters
85
+
86
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
87
+
88
+ #### Speeds, Sizes, Times [optional]
89
+
90
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
91
+
92
+ [More Information Needed]
93
+
94
+ ## Evaluation
95
+
96
+ <!-- This section describes the evaluation protocols and provides the results. -->
97
+
98
+ ### Testing Data, Factors & Metrics
99
+
100
+ #### Testing Data
101
+
102
+ <!-- This should link to a Data Card if possible. -->
103
+
104
+ [More Information Needed]
105
+
106
+ #### Factors
107
+
108
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
109
+
110
+ [More Information Needed]
111
+
112
+ #### Metrics
113
+
114
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
115
+
116
+ [More Information Needed]
117
+
118
+ ### Results
119
+
120
+ [More Information Needed]
121
+
122
+ #### Summary
123
+
124
+
125
+
126
+ ## Model Examination [optional]
127
+
128
+ <!-- Relevant interpretability work for the model goes here -->
129
+
130
+ [More Information Needed]
131
+
132
+ ## Environmental Impact
133
+
134
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
135
+
136
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
137
+
138
+ - **Hardware Type:** 8xA100s (accomplished while I was downloading the model I was actually training.)
139
+ - **Minutes used:** 25
140
+ - **Cloud Provider:** LambdaGPU
141
+ - **Compute Region:** USA
142
+ - **Carbon Emitted:** [More Information Needed]
143
+
144
+ ## Technical Specifications [optional]
145
+
146
+ ### Model Architecture and Objective
147
+
148
+ [More Information Needed]
149
+
150
+ ### Compute Infrastructure
151
+
152
+ [More Information Needed]
153
+
154
+ #### Hardware
155
+
156
+ [More Information Needed]
157
+
158
+ #### Software
159
+
160
+ [More Information Needed]
161
+
162
+ ## Citation [optional]
163
+
164
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
165
+
166
+ **BibTeX:**
167
+
168
+ [More Information Needed]
169
+
170
+ **APA:**
171
+
172
+ [More Information Needed]
173
+
174
+ ## Glossary [optional]
175
+
176
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
177
+
178
+ [More Information Needed]
179
+
180
+ ## More Information [optional]
181
+
182
+ [More Information Needed]
183
+
184
+ ## Model Card Authors [optional]
185
+
186
+ [More Information Needed]
187
+
188
+ ## Model Card Contact
189
+
190
+ [More Information Needed]