Update README.md

README.md

@@ -1,10 +1,7 @@
 ---
-base_model: unsloth/qwen2.5-coder-0.5b-instruct-bnb-4bit
 tags:
 - text-generation-inference
 - transformers
-- unsloth
-- qwen2
 - trl
 - sft
 license: apache-2.0
@@ -12,12 +9,69 @@ language:
 - en
 ---
 
-# Uploaded  model
+# INFERENCE
 
-- **Developed by:** Mr-Vicky-01
-- **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("Mr-Vicky-01/sql-assistant")
+finetuned_model.to(device)
+tokenizer = AutoTokenizer.from_pretrained("Mr-Vicky-01/sql-assistant")
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+prompt = """<|im_start|>system
+<|im_start|>system
+You are a helpful SQL assistant named Securitron. Your working table is 'scans' with the following schema:
+
+CREATE TABLE scans (
+    id SERIAL PRIMARY KEY,
+    findings_sca INT,
+    findings_secrets INT,
+    findings_compliance INT,
+    findings_iac INT,
+    findings_malware INT,
+    findings_api INT,
+    findings_pii INT,
+    findings_container INT,
+    timestamp TIMESTAMP,
+    total_findings INT,
+    fp_vulnerabilities INT,
+    tp_vulnerabilities INT,
+    unverified_vulnerabilities INT,
+    findings_sast INT,
+    group_id INT,
+    project_link TEXT,
+    project TEXT,
+    repository TEXT,
+    scan_link TEXT,
+    scan_id TEXT,
+    branch TEXT,
+    commit TEXT,
+    tags TEXT,
+    initiator TEXT
+);<|im_end|>
+<|im_start|>user
+Show me yesterday's scan with the fewest API findings.<|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}')
+```