cnatale commited on
Commit
4462944
1 Parent(s): 91e60b5

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +171 -0
README.md ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ pipeline_tag: text-generation
4
+ tags:
5
+ - finetuned
6
+ inference: false
7
+ ---
8
+
9
+ # Model Card for Model ID
10
+
11
+ This is a fine-tuned version of [Mistral 7b Instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1/).
12
+ It was fine-tuned on text to SQL in Athena/Presto dialect using the following dataset: [https://huggingface.co/datasets/cnatale/presto-athena-txt-2-sql/](https://huggingface.co/datasets/cnatale/presto-athena-txt-2-sql/)
13
+
14
+ ## Model Details
15
+
16
+ ### Model Description
17
+
18
+ - **Developed by:** Chris Natale
19
+ - **License:** Apache 2.0
20
+ - **Finetuned from model ** [https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)
21
+
22
+
23
+ ## Uses
24
+
25
+ Text to SQL in the Athena/Presto dialect.
26
+
27
+
28
+ ## Bias, Risks, and Limitations
29
+
30
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
31
+
32
+ [More Information Needed]
33
+
34
+ ### Recommendations
35
+
36
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
37
+
38
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
39
+
40
+ ## How to Get Started with the Model
41
+
42
+ Use the code below to get started with the model.
43
+
44
+ [More Information Needed]
45
+
46
+ ## Training Details
47
+
48
+ ### Training Data
49
+
50
+ <!-- This should link to a Dataset 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. -->
51
+
52
+ [More Information Needed]
53
+
54
+ ### Training Procedure
55
+
56
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
57
+
58
+ #### Preprocessing [optional]
59
+
60
+ [More Information Needed]
61
+
62
+
63
+ #### Training Hyperparameters
64
+
65
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
66
+
67
+ #### Speeds, Sizes, Times [optional]
68
+
69
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
70
+
71
+ [More Information Needed]
72
+
73
+ ## Evaluation
74
+
75
+ <!-- This section describes the evaluation protocols and provides the results. -->
76
+
77
+ ### Testing Data, Factors & Metrics
78
+
79
+ #### Testing Data
80
+
81
+ <!-- This should link to a Dataset Card if possible. -->
82
+
83
+ [More Information Needed]
84
+
85
+ #### Factors
86
+
87
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
88
+
89
+ [More Information Needed]
90
+
91
+ #### Metrics
92
+
93
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
94
+
95
+ [More Information Needed]
96
+
97
+ ### Results
98
+
99
+ [More Information Needed]
100
+
101
+ #### Summary
102
+
103
+
104
+
105
+ ## Model Examination [optional]
106
+
107
+ <!-- Relevant interpretability work for the model goes here -->
108
+
109
+ [More Information Needed]
110
+
111
+ ## Environmental Impact
112
+
113
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
114
+
115
+ 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).
116
+
117
+ - **Hardware Type:** [More Information Needed]
118
+ - **Hours used:** [More Information Needed]
119
+ - **Cloud Provider:** [More Information Needed]
120
+ - **Compute Region:** [More Information Needed]
121
+ - **Carbon Emitted:** [More Information Needed]
122
+
123
+ ## Technical Specifications [optional]
124
+
125
+ ### Model Architecture and Objective
126
+
127
+ [More Information Needed]
128
+
129
+ ### Compute Infrastructure
130
+
131
+ [More Information Needed]
132
+
133
+ #### Hardware
134
+
135
+ [More Information Needed]
136
+
137
+ #### Software
138
+
139
+ [More Information Needed]
140
+
141
+ ## Citation [optional]
142
+
143
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
144
+
145
+ **BibTeX:**
146
+
147
+ [More Information Needed]
148
+
149
+ **APA:**
150
+
151
+ [More Information Needed]
152
+
153
+ ## Glossary [optional]
154
+
155
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
156
+
157
+ [More Information Needed]
158
+
159
+ ## More Information [optional]
160
+
161
+ [More Information Needed]
162
+
163
+ ## Model Card Authors [optional]
164
+
165
+ [More Information Needed]
166
+
167
+ ## Model Card Contact
168
+
169
+ [More Information Needed]
170
+
171
+