Update README.md

README.md

@@ -1,7 +1,30 @@
 ---
 license: apache-2.0
 ---
+## llama-2-7b-miniguanaco
 
-LLama-2-7b model finetuned with miniguanaco datasets.
+This is my first model, with LLama-2-7b model finetuned with miniguanaco datasets.
 
 This is a simple finetune based off a Google Colab notebook. Finetune instructions were from Labonne's first tutorial. 
+
+To run it:
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import math
+
+model_path = "decruz07/llama-2-7b-miniguanaco"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
+)
+print(model)
+prompt = input("please input prompt:")
+while len(prompt) > 0:
+  input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
+
+  generation_output = model.generate(
+    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
+  )
+  print(tokenizer.decode(generation_output[0]))
+  prompt = input("please input prompt:")