Replaced links from sgnlp to sgnlp-models
Browse files
README.md
CHANGED
@@ -71,10 +71,10 @@ from sgnlp.models.coherence_momentum import CoherenceMomentumModel, CoherenceMom
|
|
71 |
|
72 |
# Load Model
|
73 |
config = CoherenceMomentumConfig.from_pretrained(
|
74 |
-
"https://storage.googleapis.com/sgnlp/models/coherence_momentum/config.json"
|
75 |
)
|
76 |
model = CoherenceMomentumModel.from_pretrained(
|
77 |
-
"https://storage.googleapis.com/sgnlp/models/coherence_momentum/pytorch_model.bin",
|
78 |
config=config
|
79 |
)
|
80 |
|
@@ -113,10 +113,10 @@ Please contact the authors to get the dataset if you have a valid LDC license.
|
|
113 |
#### Training Results
|
114 |
- **Training Time:** ~24 hours for ~46000 steps (batch size of 1) on a single A100 GPU
|
115 |
- **Datasets:** Permuted dataset derived from Linguistic Data Consortium's (LDC) Wall Street Journal (WSJ) dataset.
|
116 |
-
- **Training Config:** [link](https://storage.googleapis.com/sgnlp/models/coherence_momentum/config.json)
|
117 |
|
118 |
# Model Parameters
|
119 |
-
- **Model Weights:** [link](https://storage.googleapis.com/sgnlp/models/coherence_momentum/pytorch_model.bin)
|
120 |
- **Model Inputs:** A paragraph of text. During training, each positive example can be paired with one or more negative examples.
|
121 |
- **Model Outputs:** Coherence score for the input text.
|
122 |
- **Model Size:** ~930MB
|
|
|
71 |
|
72 |
# Load Model
|
73 |
config = CoherenceMomentumConfig.from_pretrained(
|
74 |
+
"https://storage.googleapis.com/sgnlp-models/models/coherence_momentum/config.json"
|
75 |
)
|
76 |
model = CoherenceMomentumModel.from_pretrained(
|
77 |
+
"https://storage.googleapis.com/sgnlp-models/models/coherence_momentum/pytorch_model.bin",
|
78 |
config=config
|
79 |
)
|
80 |
|
|
|
113 |
#### Training Results
|
114 |
- **Training Time:** ~24 hours for ~46000 steps (batch size of 1) on a single A100 GPU
|
115 |
- **Datasets:** Permuted dataset derived from Linguistic Data Consortium's (LDC) Wall Street Journal (WSJ) dataset.
|
116 |
+
- **Training Config:** [link](https://storage.googleapis.com/sgnlp-models/models/coherence_momentum/config.json)
|
117 |
|
118 |
# Model Parameters
|
119 |
+
- **Model Weights:** [link](https://storage.googleapis.com/sgnlp-models/models/coherence_momentum/pytorch_model.bin)
|
120 |
- **Model Inputs:** A paragraph of text. During training, each positive example can be paired with one or more negative examples.
|
121 |
- **Model Outputs:** Coherence score for the input text.
|
122 |
- **Model Size:** ~930MB
|