Update README.md

README.md

@@ -106,22 +106,38 @@ Our training dataset contains:
 * Polish Wikipedia: 970 million tokens
 * web crawl data: 813 million tokens
 
-## How to Use
+### Quickstart
 
-Our model is fully compatible with HuggingFace - you can use it right away.
+This model can be easily loaded using the AutoModelForCausalLM functionality.
 
-Regarding the full precision, it can be run on a graphic card with 6 GB VRAM.
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_name = "Azurro/APT-1B-Base"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+```
+
+In order to reduce the memory usage, you can use smaller precision (`bfloat16`).
 
 ```python
-import transformers
-model = transformers.AutoModelForCausalLM.from_pretrained('Azurro/APT-1B-Base')
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
 ```
 
-In order to reduce the memory usage, you can use smaller precision (bfloat16) and run the model on a graphic card with 4 GB VRAM.
+And then you can use Hugging Face Pipelines to generate text.
 
 ```python
 import transformers
-model = transformers.AutoModelForCausalLM.from_pretrained('Azurro/APT-1B-Base', torch_dtype=torch.bfloat16)
+
+text = "Najważniejszym celem człowieka na ziemi jest"
+
+pipeline = transformers.pipeline("text-generation", model=model, tokenizer=tokenizer)
+sequences = pipeline(max_length=100, do_sample=True, top_k=10, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+for seq in sequences:
+    print(f"Result: {seq['generated_text']}")
 ```
 
 ## Limitations and Biases