Danswer commited on
Commit
88794fd
1 Parent(s): 5cfa4d6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -149
README.md CHANGED
@@ -3,8 +3,6 @@ license: mit
3
  language:
4
  - en
5
  library_name: keras
6
- tags:
7
- - code
8
  ---
9
  # Model Card for Model ID
10
 
@@ -13,21 +11,18 @@ tags:
13
  This model is used to classify the user-intent for the Danswer project, visit https://github.com/danswer-ai/danswer.
14
 
15
  ## Model Details
16
- Trained multiclass classifier on top of distilbert-base-uncased
17
 
18
  ### Model Description
19
 
20
  <!-- Provide a longer summary of what this model is. -->
21
- Classifiers user intent into categories including:
22
  0: Keyword Search
23
  1: Semantic Search
24
  2: Direct Question Answering
25
 
26
 
27
  - **Developed by:** [DanswerAI]
28
- - **Shared by [optional]:** [More Information Needed]
29
- - **Model type:** [More Information Needed]
30
- - **Language(s) (NLP):** [More Information Needed]
31
  - **License:** [MIT]
32
  - **Finetuned from model [optional]:** [distilbert-base-uncased]
33
 
@@ -35,171 +30,55 @@ Classifiers user intent into categories including:
35
 
36
  <!-- Provide the basic links for the model. -->
37
 
38
- - **Repository:** [More Information Needed]
39
- - **Paper [optional]:** [More Information Needed]
40
- - **Demo [optional]:** [More Information Needed]
41
 
42
  ## Uses
43
 
44
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
45
 
46
- ### Direct Use
47
 
48
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
49
-
50
- [More Information Needed]
51
-
52
- ### Downstream Use [optional]
53
-
54
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
55
-
56
- [More Information Needed]
57
-
58
- ### Out-of-Scope Use
59
-
60
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
61
-
62
- [More Information Needed]
63
 
64
  ## Bias, Risks, and Limitations
65
 
66
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
67
 
68
- [More Information Needed]
69
 
70
  ### Recommendations
71
 
72
  <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
73
 
74
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
75
 
76
  ## How to Get Started with the Model
77
 
78
- Use the code below to get started with the model.
79
-
80
- [More Information Needed]
81
-
82
- ## Training Details
83
-
84
- ### Training Data
85
-
86
- <!-- 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. -->
87
-
88
- [More Information Needed]
89
-
90
- ### Training Procedure
91
-
92
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
93
-
94
- #### Preprocessing [optional]
95
-
96
- [More Information Needed]
97
-
98
-
99
- #### Training Hyperparameters
100
-
101
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
102
-
103
- #### Speeds, Sizes, Times [optional]
104
-
105
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
106
-
107
- [More Information Needed]
108
-
109
- ## Evaluation
110
-
111
- <!-- This section describes the evaluation protocols and provides the results. -->
112
-
113
- ### Testing Data, Factors & Metrics
114
-
115
- #### Testing Data
116
-
117
- <!-- This should link to a Data Card if possible. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Factors
122
-
123
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
124
-
125
- [More Information Needed]
126
-
127
- #### Metrics
128
-
129
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
130
-
131
- [More Information Needed]
132
-
133
- ### Results
134
-
135
- [More Information Needed]
136
-
137
- #### Summary
138
-
139
-
140
-
141
- ## Model Examination [optional]
142
-
143
- <!-- Relevant interpretability work for the model goes here -->
144
-
145
- [More Information Needed]
146
-
147
- ## Environmental Impact
148
-
149
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
150
-
151
- 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).
152
-
153
- - **Hardware Type:** [More Information Needed]
154
- - **Hours used:** [More Information Needed]
155
- - **Cloud Provider:** [More Information Needed]
156
- - **Compute Region:** [More Information Needed]
157
- - **Carbon Emitted:** [More Information Needed]
158
-
159
- ## Technical Specifications [optional]
160
-
161
- ### Model Architecture and Objective
162
-
163
- [More Information Needed]
164
-
165
- ### Compute Infrastructure
166
-
167
- [More Information Needed]
168
-
169
- #### Hardware
170
-
171
- [More Information Needed]
172
-
173
- #### Software
174
-
175
- [More Information Needed]
176
-
177
- ## Citation [optional]
178
-
179
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
180
-
181
- **BibTeX:**
182
-
183
- [More Information Needed]
184
-
185
- **APA:**
186
-
187
- [More Information Needed]
188
-
189
- ## Glossary [optional]
190
-
191
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
192
 
193
- [More Information Needed]
 
194
 
195
- ## More Information [optional]
 
 
 
 
196
 
197
- [More Information Needed]
 
198
 
199
- ## Model Card Authors [optional]
 
200
 
201
- [More Information Needed]
 
202
 
203
- ## Model Card Contact
 
204
 
205
- [More Information Needed]
 
 
3
  language:
4
  - en
5
  library_name: keras
 
 
6
  ---
7
  # Model Card for Model ID
8
 
 
11
  This model is used to classify the user-intent for the Danswer project, visit https://github.com/danswer-ai/danswer.
12
 
13
  ## Model Details
14
+ Multiclass classifier on top of distilbert-base-uncased
15
 
16
  ### Model Description
17
 
18
  <!-- Provide a longer summary of what this model is. -->
19
+ Classifies user intent of queries into categories including:
20
  0: Keyword Search
21
  1: Semantic Search
22
  2: Direct Question Answering
23
 
24
 
25
  - **Developed by:** [DanswerAI]
 
 
 
26
  - **License:** [MIT]
27
  - **Finetuned from model [optional]:** [distilbert-base-uncased]
28
 
 
30
 
31
  <!-- Provide the basic links for the model. -->
32
 
33
+ - **Repository:** [https://github.com/danswer-ai/danswer]
34
+ - **Demo [optional]:** [Upcoming!]
 
35
 
36
  ## Uses
37
 
38
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
 
40
+ This model is intended to be used in the Danswer Question-Answering System
41
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
 
43
  ## Bias, Risks, and Limitations
44
 
45
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
46
 
47
+ This model has a very small dataset maintained by DanswerAI. If interested, reach out to danswer.dev@gmail.com.
48
 
49
  ### Recommendations
50
 
51
  <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
52
 
53
+ This model is intended to be used in the Danswer (QA System)
54
 
55
  ## How to Get Started with the Model
56
 
57
+ ```
58
+ from transformers import AutoTokenizer
59
+ from transformers import TFDistilBertForSequenceClassification
60
+ import tensorflow as tf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
+ model = TFDistilBertForSequenceClassification.from_pretrained("danswer/intent-model/")
63
+ tokenizer = AutoTokenizer.from_pretrained("danswer/intent-model/")
64
 
65
+ class_semantic_mapping = {
66
+ 0: "Keyword Search",
67
+ 1: "Semantic Search",
68
+ 2: "Question Answer"
69
+ }
70
 
71
+ # Get user input
72
+ user_query = "How do I set up Danswer to run on my local environment?"
73
 
74
+ # Encode the user input
75
+ inputs = tokenizer(user_query, return_tensors="tf", truncation=True, padding=True)
76
 
77
+ # Get model predictions
78
+ predictions = model(inputs)[0]
79
 
80
+ # Get predicted class
81
+ predicted_class = tf.math.argmax(predictions, axis=-1)
82
 
83
+ print(f"Predicted class: {class_semantic_mapping[int(predicted_class)]}")
84
+ ```