Spaces:
Sleeping
Sleeping
add some space and format
Browse files
app.py
CHANGED
@@ -132,7 +132,7 @@ The dataset primarily comprises data gathered from nytimes.com and GitHub.com, s
|
|
132 |
|
133 |
- P.S. I tested ChatGPT-4.0, and the results were highly discouraging for a chunk of data consisting of 100 text filed values.
|
134 |
|
135 |
-
-In the future, we should aim to increase the dataset size to at least 10,000-15,000 samples and improve the train/test/validation split methodology.
|
136 |
""", unsafe_allow_html=False, help=None)
|
137 |
|
138 |
st.info("I crafted this dataset using a more powerful LLM and scripts, no need for boring manual labeling. The idea is to eliminate human labeling.",icon="ℹ️")
|
@@ -183,7 +183,9 @@ Given the substantial volume of data, training a model from scratch was deemed i
|
|
183 |
- Add more language in the dataset
|
184 |
### Access to the Models
|
185 |
`https://huggingface.co/wgcv/tidy-tab-model-t5-small`
|
|
|
186 |
`https://huggingface.co/wgcv/tidy-tab-model-pegasus-xsum`
|
|
|
187 |
`https://huggingface.co/wgcv/tidy-tab-model-bart-large-cnn`
|
188 |
|
189 |
## co2_eq_emissions
|
|
|
132 |
|
133 |
- P.S. I tested ChatGPT-4.0, and the results were highly discouraging for a chunk of data consisting of 100 text filed values.
|
134 |
|
135 |
+
- In the future, we should aim to increase the dataset size to at least 10,000-15,000 samples and improve the train/test/validation split methodology.
|
136 |
""", unsafe_allow_html=False, help=None)
|
137 |
|
138 |
st.info("I crafted this dataset using a more powerful LLM and scripts, no need for boring manual labeling. The idea is to eliminate human labeling.",icon="ℹ️")
|
|
|
183 |
- Add more language in the dataset
|
184 |
### Access to the Models
|
185 |
`https://huggingface.co/wgcv/tidy-tab-model-t5-small`
|
186 |
+
|
187 |
`https://huggingface.co/wgcv/tidy-tab-model-pegasus-xsum`
|
188 |
+
|
189 |
`https://huggingface.co/wgcv/tidy-tab-model-bart-large-cnn`
|
190 |
|
191 |
## co2_eq_emissions
|