Update README.md

README.md

@@ -23,4 +23,76 @@ Therefore, you have 13 apples today.
 
 You: How many oranges did I have on Saturday?
 You didn't have any oranges on Saturday because you bought 3 oranges yesterday.
+```
+
+
+
+
+# Inference Code:
+
+```python
+# pip install accelerate
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_path = "/home/migel/Tess-v2.5-Gemma-2-27b/merged"
+# model_path = "/home/migel/gemma-2-27b"
+# model_path = "google/gemma-2-27b-it"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path, 
+    device_map="auto",
+    torch_dtype=torch.bfloat16
+)
+
+terminators = [
+    tokenizer.convert_tokens_to_ids("<end_of_turn>"),
+]
+
+
+def generate_text(llm_prompt):
+    inputs = tokenizer.encode(llm_prompt, add_special_tokens=False, return_tensors="pt")
+    input_ids = inputs.to("cuda")
+    length = len(input_ids[0])
+
+    instance = {
+        "top_p": 1.0,
+        "temperature": 0.75,
+        "generate_len": 1024,
+        "top_k": 50,
+    }
+
+    generation = model.generate(
+        input_ids, 
+        max_length=length + instance["generate_len"],
+        use_cache=True,
+        do_sample=True,
+        top_p=instance["top_p"],
+        temperature=instance["temperature"],
+        top_k=instance["top_k"],
+        num_return_sequences=1,
+        pad_token_id=tokenizer.eos_token_id,
+        eos_token_id=terminators,
+    )
+    # rest= tokenizer.decode(generation[0])
+    output = generation[0][length:]
+    string = tokenizer.decode(output, skip_special_tokens=True)
+    return f"{string}"
+
+
+# conversation = f"""<|im_start|>system\nYou are Tesoro, a helful AI assitant. You always provide detailed answers without hesitation. No follow-up questions necessary.<|im_end|>\n<|im_start|>user\n"""
+
+conversation = f"""<bos><start_of_turn>user\n"""
+# conversation = f"""Write a long poem about statins."""
+
+while True:
+    user_input = input("You: ")
+    llm_prompt = f"{conversation}{user_input}<end_of_turn>\n<start_of_turn>model\n"
+    # llm_prompt = f"{conversation}{user_input}"
+    answer = generate_text(llm_prompt)
+    print(answer)
+    conversation = f"{llm_prompt}{answer}\n<start_of_turn>user\n"
+    json_data = {"prompt": user_input, "answer": answer}
+
 ```