Update README.md

README.md

@@ -318,9 +318,9 @@ pipeline_tag: zero-shot-classification
 
 This is [DeBERTa-v3-base](https://hf.co/microsoft/deberta-v3-base) fine-tuned with multi-task learning on 600 tasks of the [tasksource collection](https://github.com/sileod/tasksource/).
 This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI), and can be used for:
-- Zero-shot entailment-based classification pipeline (similar to bart-mnli), see [ZS].
-- Natural language inference, and many other tasks with tasksource-adapters, see [TA]
-- Further fine-tuning with a new task (classification, token classification or multiple-choice).
+- Zero-shot entailment-based classification pipeline (similar to bart-mnli), see [ZS]([ZS] Zero-shot classification pipeline).
+- Natural language inference, and many other tasks with tasksource-adapters, see [TA]([TA] Tasksource-adapters: 1 line access to hundreds of tasks).
+- Further fine-tuning with a new task (classification, token classification or multiple-choice) [FT]([FT] Tasknet: 3 lines fine-tuning).
 
 # [ZS] Zero-shot classification pipeline
 ```python
@@ -336,7 +336,7 @@ NLI training data of this model includes [label-nli](https://huggingface.co/data
 # [TA] Tasksource-adapters: 1 line access to hundreds of tasks 
 
 ```python
-!pip install tasknet tasksource
+# !pip install tasknet
 import tasknet as tn
 pipe = tn.load_pipeline('sileod/deberta-v3-base-tasksource-nli','glue/sst2') # works for 500+ tasksource tasks
 pipe(['That movie was great !', 'Awful movie.'])
@@ -346,6 +346,16 @@ The list of tasks is available in model config.json.
 This is more efficient than ZS since it requires only one forward pass per example, but it is less flexible.
 
 
+# [FT] Tasknet: 3 lines fine-tuning
+
+```python
+# !pip install tasknet
+import tasknet as tn
+hparams=dict(model_name='sileod/deberta-v3-base-tasksource-nli', learning_rate=2e-5)
+model, trainer = tn.Model_Trainer([tn.AutoTask("glue/rte")], hparams)
+trainer.train()
+```
+
 ## Evaluation
 This model ranked 1st among all models with the microsoft/deberta-v3-base architecture according to the IBM model recycling evaluation.
 https://ibm.github.io/model-recycling/