Commit
•
2fb241f
1
Parent(s):
8b1b829
Update README.md
Browse files
README.md
CHANGED
@@ -10,4 +10,190 @@ tags:
|
|
10 |
- medical
|
11 |
- chemistry
|
12 |
- text-generation-inference
|
13 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
- medical
|
11 |
- chemistry
|
12 |
- text-generation-inference
|
13 |
+
---
|
14 |
+
# Model Card for Model ID
|
15 |
+
This modelcard describes a fine-tuned GPT-2 language model for medical research using a personally collected dataset.
|
16 |
+
The model is intended for text generation in the medical research domain.
|
17 |
+
## Model Details
|
18 |
+
This modelcard describes a fine-tuned GPT-2 language model for medical research using a personally collected dataset. The model is intended for text generation in the medical research domain.
|
19 |
+
|
20 |
+
### Model Description
|
21 |
+
The model has been fine-tuned on a GPT-2 architecture and trained with a task-specific parameter for text generation. The do_sample parameter is set to true, which means that the model can generate text on its own rather than simply copying from the input. The max_length parameter is set to 50, which means that the maximum length of the generated text will be 50 tokens.
|
22 |
+
|
23 |
+
- **Developed by:** [OpenAI]
|
24 |
+
- **Shared by [optional]:** [More Information Needed]
|
25 |
+
- **Model type:** [Language Model]
|
26 |
+
- **Language(s) (NLP):** [More Information Needed]
|
27 |
+
- **License:** [More Information Needed]
|
28 |
+
- **Finetuned from model [optional]:** [GPT-2]
|
29 |
+
|
30 |
+
### Model Sources [optional]
|
31 |
+
|
32 |
+
<!-- Provide the basic links for the model. -->
|
33 |
+
|
34 |
+
- **Repository:** [More Information Needed]
|
35 |
+
- **Paper [optional]:** [More Information Needed]
|
36 |
+
- **Demo [optional]:** [More Information Needed]
|
37 |
+
|
38 |
+
## Uses
|
39 |
+
|
40 |
+
|
41 |
+
### Direct Use
|
42 |
+
|
43 |
+
This model can be used for text generation in the medical research domain. It can be used to generate text for a variety of purposes, such as research papers, reports, and summaries.
|
44 |
+
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
The model can be fine-tuned for downstream tasks such as summarization, question answering, and text classification.
|
49 |
+
|
50 |
+
|
51 |
+
### Out-of-Scope Use
|
52 |
+
|
53 |
+
This model may not perform as well on text outside the medical research domain. It is important to carefully evaluate the generated text to ensure that it is appropriate for the intended use.
|
54 |
+
|
55 |
+
## Bias, Risks, and Limitations
|
56 |
+
This modelcard acknowledges that all language models have limitations and potential biases. The model may produce biased or inaccurate outputs if the input data contains bias or if the training data is not diverse enough. The risks of using the model include the possibility of generating misleading or harmful information.
|
57 |
+
|
58 |
+
### Recommendations
|
59 |
+
To mitigate potential risks and limitations, users of the model should carefully evaluate the generated text and consider the following recommendations:
|
60 |
+
1)Evaluate the input data for potential bias and ensure that it is diverse and representative.
|
61 |
+
2)Consider fine-tuning the model on additional data to improve its accuracy and reduce the risk of bias.
|
62 |
+
3)Review and edit the generated text before use to ensure that it is appropriate for the intended purpose.
|
63 |
+
4)Provide clear and transparent documentation of the model's limitations and potential biases to users and stakeholders.
|
64 |
+
## How to Get Started with the Model
|
65 |
+
To use the model, load it in your preferred programming language using the transformers library, and pass in the input text. The model will generate text based on the input, using the task-specific parameters that have been set.
|
66 |
+
|
67 |
+
|
68 |
+
## Training Details
|
69 |
+
|
70 |
+
### Training Data
|
71 |
+
|
72 |
+
<!-- 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. -->
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
### Training Procedure
|
77 |
+
|
78 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
79 |
+
|
80 |
+
#### Preprocessing [optional]
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
|
85 |
+
#### Training Hyperparameters
|
86 |
+
|
87 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
88 |
+
|
89 |
+
#### Speeds, Sizes, Times [optional]
|
90 |
+
|
91 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
92 |
+
|
93 |
+
[More Information Needed]
|
94 |
+
|
95 |
+
## Evaluation
|
96 |
+
|
97 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
98 |
+
|
99 |
+
### Testing Data, Factors & Metrics
|
100 |
+
|
101 |
+
#### Testing Data
|
102 |
+
|
103 |
+
<!-- This should link to a Data Card if possible. -->
|
104 |
+
|
105 |
+
[More Information Needed]
|
106 |
+
|
107 |
+
#### Factors
|
108 |
+
|
109 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
110 |
+
|
111 |
+
[More Information Needed]
|
112 |
+
|
113 |
+
#### Metrics
|
114 |
+
|
115 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
116 |
+
|
117 |
+
[More Information Needed]
|
118 |
+
|
119 |
+
### Results
|
120 |
+
|
121 |
+
|
122 |
+
![Screenshot 2023-05-05 092541.png](https://s3.amazonaws.com/moonup/production/uploads/641ee41d863b87326f45a5f1/9gMBxc270uN8agP8n6-5m.png)
|
123 |
+
![Screenshot 2023-05-05 094102.png](https://s3.amazonaws.com/moonup/production/uploads/641ee41d863b87326f45a5f1/kqOUgU2wyxLDP1gKnCKPC.png)
|
124 |
+
![Screenshot 2023-05-05 094303.png](https://s3.amazonaws.com/moonup/production/uploads/641ee41d863b87326f45a5f1/WpNXVBwbLCNNvWJ65dJI8.png)
|
125 |
+
![Screenshot 2023-05-05 094409.png](https://s3.amazonaws.com/moonup/production/uploads/641ee41d863b87326f45a5f1/HZ1YdlwfZAi8CPlvrcqDr.png)
|
126 |
+
![Screenshot 2023-05-05 094542.png](https://s3.amazonaws.com/moonup/production/uploads/641ee41d863b87326f45a5f1/h9EJw9fRNMBpOwJVVw6zI.png)
|
127 |
+
|
128 |
+
|
129 |
+
#### Summary
|
130 |
+
|
131 |
+
|
132 |
+
|
133 |
+
## Model Examination [optional]
|
134 |
+
|
135 |
+
<!-- Relevant interpretability work for the model goes here -->
|
136 |
+
|
137 |
+
[More Information Needed]
|
138 |
+
|
139 |
+
## Environmental Impact
|
140 |
+
|
141 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
142 |
+
|
143 |
+
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).
|
144 |
+
|
145 |
+
- **Hardware Type:** [More Information Needed]
|
146 |
+
- **Hours used:** [More Information Needed]
|
147 |
+
- **Cloud Provider:** [More Information Needed]
|
148 |
+
- **Compute Region:** [More Information Needed]
|
149 |
+
- **Carbon Emitted:** [More Information Needed]
|
150 |
+
|
151 |
+
## Technical Specifications [optional]
|
152 |
+
|
153 |
+
### Model Architecture and Objective
|
154 |
+
|
155 |
+
[More Information Needed]
|
156 |
+
|
157 |
+
### Compute Infrastructure
|
158 |
+
|
159 |
+
[More Information Needed]
|
160 |
+
|
161 |
+
#### Hardware
|
162 |
+
|
163 |
+
[More Information Needed]
|
164 |
+
|
165 |
+
#### Software
|
166 |
+
|
167 |
+
[More Information Needed]
|
168 |
+
|
169 |
+
## Citation [optional]
|
170 |
+
|
171 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
172 |
+
|
173 |
+
**BibTeX:**
|
174 |
+
|
175 |
+
[More Information Needed]
|
176 |
+
|
177 |
+
**APA:**
|
178 |
+
|
179 |
+
[More Information Needed]
|
180 |
+
|
181 |
+
## Glossary [optional]
|
182 |
+
|
183 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
184 |
+
|
185 |
+
[More Information Needed]
|
186 |
+
|
187 |
+
## More Information [optional]
|
188 |
+
|
189 |
+
[More Information Needed]
|
190 |
+
|
191 |
+
## Model Card Authors [optional]
|
192 |
+
|
193 |
+
[More Information Needed]
|
194 |
+
|
195 |
+
## Model Card Contact
|
196 |
+
|
197 |
+
[More Information Needed]
|
198 |
+
|
199 |
+
|