Rename README.md to update(code): fix tokenizer loading

README.md → update(code): fix tokenizer loading

@@ -31,11 +31,9 @@ license: other
 `StableLM 2 Zephyr 1.6B` uses the following instruction format:
 ```
 <|user|>
-List 3 synonyms for the word "tiny"<|endoftext|>
+Which famous math number begins with 1.6 ...?<|endoftext|>
 <|assistant|>
-1. Dwarf
-2. Little
-3. Petite<|endoftext|>
+The number you are referring to is 1.618033988749895. This is the famous value known as the golden ratio<|endoftext|>
 ```
 
 This format is also available through the tokenizer's `apply_chat_template` method:
@@ -43,14 +41,14 @@ This format is also available through the tokenizer's `apply_chat_template` meth
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-tokenizer = AutoTokenizer.from_pretrained('stabilityai/stablelm-zephyr-3b')
+tokenizer = AutoTokenizer.from_pretrained('stabilityai/stablelm-2-zephyr-1_6b', trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     'stabilityai/stablelm-2-zephyr-1_6b',
     trust_remote_code=True,
     device_map="auto"
 )
 
-prompt = [{'role': 'user', 'content': 'List 3 synonyms for the word "tiny"'}]
+prompt = [{'role': 'user', 'content': 'Which famous math number begins with 1.6 ...?'}]
 inputs = tokenizer.apply_chat_template(
     prompt,
     add_generation_prompt=True,
@@ -60,7 +58,7 @@ inputs = tokenizer.apply_chat_template(
 tokens = model.generate(
     inputs.to(model.device),
     max_new_tokens=1024,
-    temperature=0.8,
+    temperature=0.5,
     do_sample=True
 )