Instructions to use evankomp/learn2therm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use evankomp/learn2therm with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="evankomp/learn2therm")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("evankomp/learn2therm") model = AutoModelForSequenceClassification.from_pretrained("evankomp/learn2therm", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,6 +28,7 @@ __Training__:
|
|
| 28 |
ProteinBERT (Rostlab/prot_bert) was fine tuned on a class balanced version of learn2therm (see [here]()), about 250k protein amino acid sequences.
|
| 29 |
|
| 30 |
Training parameters below:
|
|
|
|
| 31 |
TrainingArguments(
|
| 32 |
_n_gpu=1,
|
| 33 |
adafactor=False,
|
|
@@ -134,6 +135,6 @@ warmup_steps=0,
|
|
| 134 |
weight_decay=0.0,
|
| 135 |
xpu_backend=None,
|
| 136 |
)
|
| 137 |
-
|
| 138 |
|
| 139 |
See the [training repository](https://github.com/BeckResearchLab/learn2thermML) for code.
|
|
|
|
| 28 |
ProteinBERT (Rostlab/prot_bert) was fine tuned on a class balanced version of learn2therm (see [here]()), about 250k protein amino acid sequences.
|
| 29 |
|
| 30 |
Training parameters below:
|
| 31 |
+
```
|
| 32 |
TrainingArguments(
|
| 33 |
_n_gpu=1,
|
| 34 |
adafactor=False,
|
|
|
|
| 135 |
weight_decay=0.0,
|
| 136 |
xpu_backend=None,
|
| 137 |
)
|
| 138 |
+
```
|
| 139 |
|
| 140 |
See the [training repository](https://github.com/BeckResearchLab/learn2thermML) for code.
|