Update README.md

README.md

@@ -1,22 +1,62 @@
 ---
-base_model: unsloth/qwen2.5-coder-0.5b-instruct-bnb-4bit
 tags:
 - text-generation-inference
 - transformers
-- unsloth
-- qwen2
 - trl
+- sft
 license: apache-2.0
 language:
 - en
 ---
 
-# Uploaded  model
+# INFERENCE
 
-- **Developed by:** AquilaX-AI
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/qwen2.5-coder-0.5b-instruct-bnb-4bit
+```python
+import time
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
 
-This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+finetuned_model = AutoModelForCausalLM.from_pretrained("AquilaX-AI/security_assistant_2")
+tokenizer = AutoTokenizer.from_pretrained("AquilaX-AI/security_assistant")
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+finetuned_model.to(device)
+
+prompt = """<|im_start|>system
+You are a helpful AI assistant named Securitron<|im_end|>
+<|im_start|>user
+cwe_id:CWE-20
+cwe_name:Improper Input Validation
+affected_line:Pattern Undefined (v3)
+partial_code:example: c4d5ea2f-81a2-4a05-bcd3-202126ae21df
+        name:
+          type: string
+          example: Toolbox
+        serial:
+file_name:itemit_openapi.yaml
+status:True Positive
+reason: There is no pattern property that could lead to insufficient input validation.
+remediation_action: Always define a pattern to ensure strict input validation.
+
+How to fix this?<|im_end|>
+<|im_start|>assistant
+"""
+
+s = time.time()
+
+encodeds = tokenizer(prompt, return_tensors="pt",truncation=True).input_ids.to(device)
+text_streamer = TextStreamer(tokenizer, skip_prompt = True)
+
+# Increase max_new_tokens if needed
+response = finetuned_model.generate(
+        input_ids=encodeds,
+        streamer=text_streamer,
+        max_new_tokens=512,
+        use_cache=True,
+        pad_token_id=151645,
+        eos_token_id=151645,
+        num_return_sequences=1
+    )
+e = time.time()
+print(f'time taken:{e-s}')
+```