Update README.md

README.md

@@ -39,6 +39,28 @@ metrics:
 
 ## Usage
 
+```
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "PrunaAI/mattshumer-Hermes-2-Pro-11B-bnb-4bit"
+tokenizer = "mattshumer/Hermes-2-Pro-11B"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(tokenizer)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    device_map="auto",
+    cache_dir='/nfs/students/rachwan/delete_me/hermes'
+)
+```
+
+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"])
+
 
 ## Credits & License