nickmalhotra commited on
Commit
27b2fdf
1 Parent(s): 56c92de

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +144 -109
README.md CHANGED
@@ -1,201 +1,236 @@
1
  ---
2
- license: other
3
- language:
4
- - hi
5
- library_name: adapter-transformers
6
- tags:
7
- - code
8
- ---
9
- # Model Card for Model ID
10
-
11
- The model is a single shot Instruct tuned model in Hindi and dialects
12
-
13
- This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
14
-
15
- ## Model Details
16
-
17
- ### Model Description
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
 
19
- <!-- Provide a longer summary of what this model is. -->
20
-
21
-
22
- - **Developed by:** Makers Lab
23
- - **Funded by [optional]:** NA
24
- - **Shared by [optional]:** Nikhil Malhotra
25
- - **Model type:** Foundational Instruct tuned model
26
- - **Language(s) (NLP):** Hindi, Bhojpuri, Maithili, Angika
27
- - **License:** Open
28
- - **Finetuned from model [optional]:** None
29
-
30
- ### Model Sources [optional]
31
 
32
- <!-- Provide the basic links for the model. -->
33
 
34
- - **Repository:** NA
 
35
 
36
 
37
- ## Uses
38
 
39
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
40
- Used for Q and A
41
 
42
- ### Direct Use
43
 
44
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
 
45
 
46
- [More Information Needed]
47
 
48
- ### Downstream Use [optional]
49
 
50
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
51
 
52
- [More Information Needed]
 
53
 
54
- ### Out-of-Scope Use
55
 
56
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
57
 
58
- [More Information Needed]
59
 
60
- ## Bias, Risks, and Limitations
61
 
62
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
63
 
64
- [More Information Needed]
65
 
66
- ### Recommendations
67
-
68
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
69
 
70
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
71
 
72
- ## How to Get Started with the Model
73
 
74
- Use the code below to get started with the model.
75
 
76
- [More Information Needed]
77
 
78
- ## Training Details
79
 
80
- ### Training Data
81
 
82
- <!-- 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. -->
83
 
84
- [More Information Needed]
85
 
86
- ### Training Procedure
87
 
88
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
89
 
90
- #### Preprocessing [optional]
91
 
92
- [More Information Needed]
93
 
 
94
 
95
- #### Training Hyperparameters
96
 
97
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
98
 
99
- #### Speeds, Sizes, Times [optional]
100
 
101
  <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
102
 
103
- [More Information Needed]
104
-
105
- ## Evaluation
106
 
107
  <!-- This section describes the evaluation protocols and provides the results. -->
108
 
109
- ### Testing Data, Factors & Metrics
110
 
111
- #### Testing Data
112
 
113
- <!-- This should link to a Dataset Card if possible. -->
114
 
115
- [More Information Needed]
116
 
117
- #### Factors
 
118
 
119
  <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
120
 
121
- [More Information Needed]
122
 
123
- #### Metrics
124
 
125
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
126
 
127
- [More Information Needed]
128
-
129
- ### Results
130
-
131
- [More Information Needed]
132
-
133
- #### Summary
134
 
 
135
 
 
136
 
137
- ## Model Examination [optional]
138
 
139
- <!-- Relevant interpretability work for the model goes here -->
140
 
141
- [More Information Needed]
142
-
143
- ## Environmental Impact
144
 
145
  <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
146
 
147
  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).
148
 
149
- - **Hardware Type:** [More Information Needed]
150
- - **Hours used:** [More Information Needed]
151
- - **Cloud Provider:** [More Information Needed]
152
- - **Compute Region:** [More Information Needed]
153
- - **Carbon Emitted:** [More Information Needed]
154
 
155
- ## Technical Specifications [optional]
156
 
157
- ### Model Architecture and Objective
158
 
159
- [More Information Needed]
160
 
161
- ### Compute Infrastructure
162
 
163
- [More Information Needed]
164
 
165
- #### Hardware
166
 
167
- [More Information Needed]
168
 
169
- #### Software
170
 
171
- [More Information Needed]
172
 
173
- ## Citation [optional]
174
 
175
  <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
176
 
177
  **BibTeX:**
178
 
179
- [More Information Needed]
180
 
181
  **APA:**
182
 
183
- [More Information Needed]
184
 
185
- ## Glossary [optional]
186
 
187
  <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
188
 
189
- [More Information Needed]
 
 
 
 
 
 
190
 
191
- ## More Information [optional]
192
 
193
- [More Information Needed]
194
 
195
- ## Model Card Authors [optional]
 
 
 
 
 
 
196
 
197
- [More Information Needed]
 
198
 
199
- ## Model Card Contact
200
 
201
- [More Information Needed]
 
1
  ---
2
+ # Model Card for Indus
3
+
4
+ <!-- Provide a quick summary of what the model is/does. [Optional] -->
5
+ The model is a single shot fine tuned Instruct LLM in Hindi and dialects
6
+
7
+
8
+
9
+
10
+ # Table of Contents
11
+
12
+ - [Model Card for Indus](#model-card-for--model_id-)
13
+ - [Table of Contents](#table-of-contents)
14
+ - [Table of Contents](#table-of-contents-1)
15
+ - [Model Details](#model-details)
16
+ - [Model Description](#model-description)
17
+ - [Uses](#uses)
18
+ - [Direct Use](#direct-use)
19
+ - [Downstream Use [Optional]](#downstream-use-optional)
20
+ - [Out-of-Scope Use](#out-of-scope-use)
21
+ - [Bias, Risks, and Limitations](#bias-risks-and-limitations)
22
+ - [Recommendations](#recommendations)
23
+ - [Training Details](#training-details)
24
+ - [Training Data](#training-data)
25
+ - [Training Procedure](#training-procedure)
26
+ - [Preprocessing](#preprocessing)
27
+ - [Speeds, Sizes, Times](#speeds-sizes-times)
28
+ - [Evaluation](#evaluation)
29
+ - [Testing Data, Factors & Metrics](#testing-data-factors--metrics)
30
+ - [Testing Data](#testing-data)
31
+ - [Factors](#factors)
32
+ - [Metrics](#metrics)
33
+ - [Results](#results)
34
+ - [Model Examination](#model-examination)
35
+ - [Environmental Impact](#environmental-impact)
36
+ - [Technical Specifications [optional]](#technical-specifications-optional)
37
+ - [Model Architecture and Objective](#model-architecture-and-objective)
38
+ - [Compute Infrastructure](#compute-infrastructure)
39
+ - [Hardware](#hardware)
40
+ - [Software](#software)
41
+ - [Citation](#citation)
42
+ - [Glossary [optional]](#glossary-optional)
43
+ - [More Information [optional]](#more-information-optional)
44
+ - [Model Card Authors [optional]](#model-card-authors-optional)
45
+ - [Model Card Contact](#model-card-contact)
46
+ - [How to Get Started with the Model](#how-to-get-started-with-the-model)
47
+
48
+
49
+ # Model Details
50
+
51
+ ## Model Description
52
+
53
+ <!-- Provide a longer summary of what this model is/does. -->
54
+ The model is a single shot fine tuned Instruct LLM in Hindi and dialects
55
+
56
+ - **Developed by:** More information needed
57
+ - **Shared by [Optional]:** More information needed
58
+ - **Model type:** Language model
59
+ - **Language(s) (NLP):** hin, bho, mai, doi
60
+ - **License:** other
61
+ - **Parent Model:** More information needed
62
+ - **Resources for more information:** More information needed
63
+
64
+
65
+
66
+ # Uses
67
 
68
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
 
 
 
 
 
 
 
 
 
 
69
 
70
+ ## Direct Use
71
 
72
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
73
+ <!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
74
 
75
 
 
76
 
 
 
77
 
78
+ ## Downstream Use [Optional]
79
 
80
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
81
+ <!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
82
+
83
 
 
84
 
 
85
 
86
+ ## Out-of-Scope Use
87
 
88
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
89
+ <!-- If the user enters content, print that. If not, but they enter a task in the list, use that. If neither, say "more info needed." -->
90
 
 
91
 
 
92
 
 
93
 
94
+ # Bias, Risks, and Limitations
95
 
96
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
97
 
98
+ Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
99
 
 
 
 
100
 
101
+ ## Recommendations
102
 
103
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
104
 
 
105
 
 
106
 
 
107
 
 
108
 
109
+ # Training Details
110
 
111
+ ## Training Data
112
 
113
+ <!-- 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. -->
114
 
115
+ More information on training data needed
116
 
 
117
 
118
+ ## Training Procedure
119
 
120
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
121
 
122
+ ### Preprocessing
123
 
124
+ More information needed
125
 
126
+ ### Speeds, Sizes, Times
127
 
128
  <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
129
 
130
+ More information needed
131
+
132
+ # Evaluation
133
 
134
  <!-- This section describes the evaluation protocols and provides the results. -->
135
 
136
+ ## Testing Data, Factors & Metrics
137
 
138
+ ### Testing Data
139
 
140
+ <!-- This should link to a Data Card if possible. -->
141
 
142
+ More information needed
143
 
144
+
145
+ ### Factors
146
 
147
  <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
148
 
149
+ More information needed
150
 
151
+ ### Metrics
152
 
153
  <!-- These are the evaluation metrics being used, ideally with a description of why. -->
154
 
155
+ More information needed
 
 
 
 
 
 
156
 
157
+ ## Results
158
 
159
+ More information needed
160
 
161
+ # Model Examination
162
 
163
+ More information needed
164
 
165
+ # Environmental Impact
 
 
166
 
167
  <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
168
 
169
  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).
170
 
171
+ - **Hardware Type:** More information needed
172
+ - **Hours used:** More information needed
173
+ - **Cloud Provider:** More information needed
174
+ - **Compute Region:** More information needed
175
+ - **Carbon Emitted:** More information needed
176
 
177
+ # Technical Specifications [optional]
178
 
179
+ ## Model Architecture and Objective
180
 
181
+ More information needed
182
 
183
+ ## Compute Infrastructure
184
 
185
+ More information needed
186
 
187
+ ### Hardware
188
 
189
+ More information needed
190
 
191
+ ### Software
192
 
193
+ More information needed
194
 
195
+ # Citation
196
 
197
  <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
198
 
199
  **BibTeX:**
200
 
201
+ More information needed
202
 
203
  **APA:**
204
 
205
+ More information needed
206
 
207
+ # Glossary [optional]
208
 
209
  <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
210
 
211
+ More information needed
212
+
213
+ # More Information [optional]
214
+
215
+ More information needed
216
+
217
+ # Model Card Authors [optional]
218
 
219
+ <!-- This section provides another layer of transparency and accountability. Whose views is this model card representing? How many voices were included in its construction? Etc. -->
220
 
221
+ Nikhil Malhotra, Nilesh Brahme, Vinay Sharma, Satish Mishra
222
 
223
+ # Model Card Contact
224
+
225
+ More information needed
226
+
227
+ # How to Get Started with the Model
228
+
229
+ Use the code below to get started with the model.
230
 
231
+ <details>
232
+ <summary> Click to expand </summary>
233
 
234
+ More information needed
235
 
236
+ </details>