add inference code

README.md

@@ -52,3 +52,37 @@ This is Bloomz-7b1-mt model fine-tuned with multilingual instruction dataset and
 - Thai
 - Vietnamese
 - Chinese
+
+## Usage
+
+Following is the code to do the inference using this model:
+```
+import torch
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+
+peft_model_id = "cahya/bloomz-7b1-instruct"
+config = PeftConfig.from_pretrained(peft_model_id)
+
+model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, 
+                                             load_in_8bit=True, device_map='auto')
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
+
+# Load the Lora model
+model = PeftModel.from_pretrained(model, peft_model_id)
+
+batch = tokenizer("User: How old is the universe?\nAssistant: ", return_tensors='pt').to(0)
+
+
+with torch.cuda.amp.autocast():
+  output_tokens = model.generate(**batch, max_new_tokens=200,
+                                 min_length=50,
+                                 do_sample=True,
+                                 top_k=40,
+                                 top_p=0.9,
+                                 temperature=0.2,
+                                 repetition_penalty=1.2,
+                                 num_return_sequences=1)
+
+print('\n\n', tokenizer.decode(output_tokens[0], skip_special_tokens=True))
+```