Update README.md
Browse files
README.md
CHANGED
@@ -27,52 +27,41 @@ It also uses a different ouput layer consisting of sigmoid activated neurons to
|
|
27 |
- **Language(s) (NLP):** Probably english (it depends heavily on dataset)
|
28 |
- **License:** Apache license 2.0
|
29 |
|
30 |
-
### Model Sources [optional]
|
31 |
-
|
32 |
-
<!-- Provide the basic links for the model. -->
|
33 |
-
|
34 |
-
- **Repository:** [More Information Needed]
|
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 |
|
41 |
### Direct Use
|
42 |
|
43 |
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
|
|
44 |
|
45 |
-
[More Information Needed]
|
46 |
-
|
47 |
-
### Downstream Use [optional]
|
48 |
-
|
49 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
50 |
-
|
51 |
-
[More Information Needed]
|
52 |
|
53 |
### Out-of-Scope Use
|
54 |
|
55 |
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
56 |
|
57 |
-
|
|
|
58 |
|
59 |
## Bias, Risks, and Limitations
|
60 |
|
61 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
62 |
-
|
63 |
-
|
64 |
|
65 |
### Recommendations
|
66 |
|
67 |
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
68 |
-
|
69 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
70 |
|
71 |
## How to Get Started with the Model
|
72 |
|
73 |
-
|
74 |
|
75 |
-
|
76 |
|
77 |
## Training Details
|
78 |
|
@@ -85,11 +74,8 @@ Use the code below to get started with the model.
|
|
85 |
### Training Procedure
|
86 |
|
87 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
[More Information Needed]
|
92 |
-
|
93 |
|
94 |
#### Training Hyperparameters
|
95 |
|
@@ -145,7 +131,7 @@ Use the code below to get started with the model.
|
|
145 |
|
146 |
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).
|
147 |
|
148 |
-
- **Hardware Type:**
|
149 |
- **Hours used:** [More Information Needed]
|
150 |
- **Cloud Provider:** [More Information Needed]
|
151 |
- **Compute Region:** [More Information Needed]
|
@@ -163,11 +149,11 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
163 |
|
164 |
#### Hardware
|
165 |
|
166 |
-
|
167 |
|
168 |
#### Software
|
169 |
|
170 |
-
|
171 |
|
172 |
## Citation [optional]
|
173 |
|
|
|
27 |
- **Language(s) (NLP):** Probably english (it depends heavily on dataset)
|
28 |
- **License:** Apache license 2.0
|
29 |
|
|
|
|
|
|
|
|
|
|
|
30 |
|
31 |
## Uses
|
32 |
|
33 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
34 |
+
This can be used for text generation tasks where running large computationally intensive architectures are not applicable
|
35 |
|
36 |
### Direct Use
|
37 |
|
38 |
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
39 |
+
For simpler text generation tasks where long range contextual understanding is not must
|
40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
|
42 |
### Out-of-Scope Use
|
43 |
|
44 |
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
45 |
|
46 |
+
Not applicable for production/commercial use
|
47 |
+
May generate illegal/bad/meaningless responses thay maybe harmful
|
48 |
|
49 |
## Bias, Risks, and Limitations
|
50 |
|
51 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
52 |
+
May generate illegal/bad/meaningless responses thay maybe harmful.
|
53 |
+
The model can't handle longer sequences larger than 50 words with contextual relevence
|
54 |
|
55 |
### Recommendations
|
56 |
|
57 |
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
58 |
+
May generate illegal/bad/meaningless responses thay maybe harmful
|
|
|
59 |
|
60 |
## How to Get Started with the Model
|
61 |
|
62 |
+
Just run the main.py file
|
63 |
|
64 |
+
almost basic documentation will be in program itself detailed manual will be in manual.txt file
|
65 |
|
66 |
## Training Details
|
67 |
|
|
|
74 |
### Training Procedure
|
75 |
|
76 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
77 |
+
Final training loss: 0.0322
|
78 |
+
Final validation loss: 5.6888
|
|
|
|
|
|
|
79 |
|
80 |
#### Training Hyperparameters
|
81 |
|
|
|
131 |
|
132 |
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).
|
133 |
|
134 |
+
- **Hardware Type:** Trained using Nvidia rtx 2050, using cudnn and cuda dependencies
|
135 |
- **Hours used:** [More Information Needed]
|
136 |
- **Cloud Provider:** [More Information Needed]
|
137 |
- **Compute Region:** [More Information Needed]
|
|
|
149 |
|
150 |
#### Hardware
|
151 |
|
152 |
+
Nvidia Geforce rtx 2050
|
153 |
|
154 |
#### Software
|
155 |
|
156 |
+
cudnn, cuda, tensorflow
|
157 |
|
158 |
## Citation [optional]
|
159 |
|