Instructions to use deshanksuman/finetunedQwen3-4B-Instruct-WSD-Verb_reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deshanksuman/finetunedQwen3-4B-Instruct-WSD-Verb_reasoning with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("deshanksuman/finetunedQwen3-4B-Instruct-WSD-Verb_reasoning", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,4 +14,29 @@ base_model:
|
|
| 14 |
|
| 15 |
Word Sense Disambiguation with Reasoning using "deshanksuman/Advance_Reasoning_for_Verb_WSD".
|
| 16 |
|
| 17 |
-
This approach is focused on syntactic and Semantic reasoning.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
Word Sense Disambiguation with Reasoning using "deshanksuman/Advance_Reasoning_for_Verb_WSD".
|
| 16 |
|
| 17 |
+
This approach is focused on syntactic and Semantic reasoning.
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- This is adapter has been trained for 5 epochs.
|
| 21 |
+
|
| 22 |
+
- Hyperparameter for Training
|
| 23 |
+
|
| 24 |
+
-
|
| 25 |
+
per_device_train_batch_size=4,
|
| 26 |
+
gradient_accumulation_steps=8,
|
| 27 |
+
warmup_steps=50,
|
| 28 |
+
num_train_epochs=2,
|
| 29 |
+
learning_rate=2e-4,
|
| 30 |
+
fp16=not torch.cuda.is_bf16_supported(),
|
| 31 |
+
bf16=torch.cuda.is_bf16_supported(),
|
| 32 |
+
logging_steps=10,
|
| 33 |
+
optim="adamw_torch",
|
| 34 |
+
weight_decay=0.01,
|
| 35 |
+
lr_scheduler_type="linear",
|
| 36 |
+
seed=3407
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
This is developed by Deshan Sumanathilaka https://sumanathilaka.github.io
|
| 40 |
+
|
| 41 |
+
- Acknowledgement
|
| 42 |
+
We acknowledge the support of the Supercomputing Wales project, which is part-funded by the European Regional Development Fund (ERDF) via Welsh Government.
|