Update README.md

README.md

@@ -28,9 +28,9 @@ widget:
 
 # T5 for belarusian language
 
-This model is based on T5-small with sequence length equal 128 tokens.
+This model is based on T5-small with sequence length equal 128 tokens. Model trained from scratch on RTX 3090  24GB. 
 
-Supported tasks:
+# Supported tasks:
   - translation BE to RU: `<extra_id_1>`
   - translation BE to EN: `<extra_id_2>`
   - translation RU to BE: `<extra_id_3>`
@@ -38,7 +38,25 @@ Supported tasks:
   - translation EN to BE: `<extra_id_6>`
   - translation EN to RU: `<extra_id_7>`
 
-Metrics:
+# Metrics:
  - [evel/BLEU](https://api.wandb.ai/links/miklgr500/31mq4s36)
  - [evel/loss](https://api.wandb.ai/links/miklgr500/rvi2p69n)
- - [train/loss](https://api.wandb.ai/links/miklgr500/z9alu3n5)
+ - [train/loss](https://api.wandb.ai/links/miklgr500/z9alu3n5)
+
+# How to Get Started with the Model
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+from transformers import T5TokenizerFast, T5ForConditionalGeneration
+
+tokenizer = T5TokenizerFast.from_pretrained("WelfCrozzo/T5-L128-belarusian")
+model = T5ForConditionalGeneration.from_pretrained("WelfCrozzo/T5-L128-belarusian")
+
+x = tokenizer.encode('<extra_id_1>да зорак праз цяжкасці', return_tensors='pt')
+
+result = model.generate(x, return_dict_in_generate=True, output_scores=True,max_length=128)
+print(tokenizer.decode(result["sequences"][0]))
+```
+</details>