Update README.md

README.md

@@ -50,22 +50,41 @@ experts:
 
 ```python
 !pip install -qU transformers bitsandbytes accelerate
-
-from transformers import AutoTokenizer
-import transformers
+from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
 import torch
 
-model = "paulilioaica/PhiMiX-2x2B"
+model_name = "paulilioaica/PhiMiX-2x2B"
+
+torch.set_default_device("cuda")
+
+config = AutoConfig.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_config(config, trust_remote_code=True)
+
+instruction = '''
+    def print_prime(n):
+        """
+        Print all primes between 1 and n
+        """
+'''
+
 
-tokenizer = AutoTokenizer.from_pretrained(model)
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model,
-    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+tokenizer = AutoTokenizer.from_pretrained(
+    f"{model_name}", 
+    trust_remote_code=True
 )
 
-messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
-prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-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"])
+# Tokenize the input string
+inputs = tokenizer(
+    instruction, 
+    return_tensors="pt", 
+    return_attention_mask=False
+)
+
+# Generate text using the model
+outputs = model.generate(**inputs, max_length=200)
+
+# Decode and print the output
+text = tokenizer.batch_decode(outputs)[0]
+print(text)
+
 ```