Update README.md

README.md

@@ -28,4 +28,42 @@ language:
 
 ### Framework versions
 
-- PEFT 0.17.1
+- PEFT 0.17.1
+
+
+### Inference Code
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+
+model_name = "Prachir-AI/Thinkmini"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Create a BitsAndBytesConfig to enable 4-bit loading
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True, # Enable 4-bit loading as intended for this model
+    bnb_4bit_quant_type="nf4", # This is a common default for 4-bit models
+    bnb_4bit_compute_dtype=torch.bfloat16, # Use bfloat16 for computation
+    bnb_4bit_use_double_quant=True, # Often used with nf4
+)
+
+# Load the model with the configured 4-bit quantization
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    quantization_config=bnb_config,
+    torch_dtype=torch.bfloat16 # Ensure the model itself is loaded with bfloat16 dtypes where applicable
+)
+
+inputs = tokenizer("How do you plan for a full pentest of a web application?", return_tensors="pt").to('cuda')
+  # inference mode
+
+output_ids = model.generate(
+    **inputs,
+    max_new_tokens=500,
+    temperature=0.7,
+    top_p=0.9
+)
+
+print(tokenizer.decode(output_ids[0], skip_special_tokens=True))
+```