Update README.md

README.md

@@ -7,6 +7,26 @@ Tulpar-7b is a LLama2-7b-based model trained by Hyperbee.ai. Training is done on
 
 # Example Usage
 
+Loading the model:
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("HyperbeeAI/Tulpar-7b-v0")
+model = AutoModelForCausalLM.from_pretrained("HyperbeeAI/Tulpar-7b-v0")
+```
+
+You can run inference with both of the following prompts:
+```python
+prompt = f"### User: {input_text}\n\n### Assistant:\n"
+inputs = tokenizer(prompt, return_tensors="pt")
+output = model.generate(**inputs, **generation_config)
+```
+
+```python
+prompt = f"Question: {input_text}\n\nAnswer:"
+inputs = tokenizer(prompt, return_tensors="pt")
+output = model.generate(**inputs, **generation_config)
+```
 
 
 # Evaluation