Update README.md

README.md

@@ -45,24 +45,38 @@ dtype: bfloat16
 ## 💻 Usage
 
 ```python
+# Installation
 !pip install -qU transformers accelerate
 
-from transformers import AutoTokenizer
-import transformers
+# Imports
+from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-model = "MrOvkill/Phi-3-Instruct-Bloated"
-messages = [{"role": "user", "content": "What is a large language model?"}]
+# Loading
+tokenizer = AutoTokenizer.from_pretrained("./merge/")
+model = AutoModelForCausalLM.from_pretrained("./merge/")
 
-tokenizer = AutoTokenizer.from_pretrained(model)
-prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model,
-    torch_dtype=torch.float16,
-    device_map="auto",
-)
+# Completion function
+def infer(prompt, **kwargs):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model.generate(**inputs, **kwargs)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Some silliness
+infer("<|user|>\nBen is going to the store for some Ice Cream. So is Jerry. They mix up the ice cream at the store. Is the ice cream: (a. Ben's (b. Jerry's (c. Ben and Jerry's <|end|>\n<|assistant|>\nMy answer is (", max_new_tokens=1024)
 
-outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
-print(outputs[0]["generated_text"])
+# A proper test
+infer(
+    """
+<|user|>
+Explain what a Mixture of Experts is in less than 100 words.
+<|assistant|>
+""",
+    max_new_tokens=1024,
+    do_sample=False,
+    temperature=0.0,
+    top_k=50,
+    top_p=0.89,
+)
 ```