Update README.md

README.md

@@ -56,3 +56,46 @@ The following `bitsandbytes` quantization config was used during training:
 
 
 - PEFT 0.6.2
+
+
+### Try the model!
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base_model = "mistralai/Mistral-7B-Instruct-v0.3"
+adapter_model = 'ifca-advanced-computing/Mistral-7B-Instruct-v0.3-EOSC'
+
+model = AutoModelForCausalLM.from_pretrained(base_model)
+model = PeftModel.from_pretrained(model, adapter_model)
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+
+model.eval()
+
+query = [
+    {"role": "user", "content": "What is the EOSC?"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    query,
+    tokenize=True,
+    return_tensors="pt"
+).to(model.device)
+
+with torch.no_grad():
+    outputs = model.generate(
+        input_ids=input_ids,
+        max_new_tokens=500,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9
+    )
+
+question = query[0]['content']
+print(f'QUESTION: {question} \n')
+
+print('ANSWER:\n')
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```