Update README.md

README.md

@@ -20,3 +20,49 @@ language:
 This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+
+
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+import torch
+import json
+
+model_id = "suriya7/qwen-1.5b-quantized"
+filename = "unsloth.Q5_K_M.gguf"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
+model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename)
+
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+sys_prompt = """<|im_start|>system\nYou are Securitron, an AI assistant specialized in detecting vulnerabilities in source code. Analyze the provided code and provide a structured report on any security issues found.<|im_end|>"""
+
+user_prompt = """
+CODE FOR SCANNING
+"""
+
+prompt = f"""{sys_prompt}
+<|im_start|>user
+{user_prompt}<|im_end|>
+<|im_start|>assistant
+"""
+
+encodeds = tokenizer(prompt, return_tensors="pt", truncation=True).input_ids.to(device)
+
+text_streamer = TextStreamer(tokenizer, skip_prompt=True)
+
+response = model.generate(
+    input_ids=encodeds,
+    streamer=text_streamer,
+    max_new_tokens=4096,
+    use_cache=True,
+    pad_token_id=151645,
+    eos_token_id=151645,
+    num_return_sequences=1
+)
+    
+output = json.loads(tokenizer.decode(response[0]).split('<|im_start|>assistant')[-1].split('<|im_end|>')[0].strip())
+```