Update README.md

README.md

@@ -16,8 +16,45 @@ vLLM with LoRA support
 
 ---
 
+## Compile and install from source
+
 ```shell
 git clone --branch support_peft https://github.com/SuperBruceJia/vllm.git
 cd vllm
 pip install -e . --user
 ```
+
+## Set-up LLM with LoRA 
+Please note that this is just a demo!
+```shell
+from vllm import LLM, SamplingParams
+from vllm.model_executor.adapters import lora
+from vllm.model_executor.parallel_utils.parallel_state import destroy_model_parallel
+
+def stop_token_list():
+    stop_tokens = ["Question:",
+                   "Question",
+                   "USER:",
+                   "USER",
+                   "ASSISTANT:",
+                   "ASSISTANT",
+                   "Instruction:",
+                   "Instruction",
+                   "Response:",
+                   "Response",]
+
+    return stop_tokens
+
+
+stop_tokens = stop_token_list()
+sampling_params = SamplingParams(temperature=0.0, top_p=1, max_tokens=128, stop=stop_tokens)
+
+llm = LLM(model="meta-llama/Llama-2-7b-hf", load_format="auto", tensor_parallel_size=1, gpu_memory_utilization=0.90)
+lora.LoRAModel.from_pretrained(llm.llm_engine.workers[0].model, '/adapter')  # The adapter saved path
+
+prompts = ["Hello World", "Hello Python"]
+completions = llm.generate(prompts, sampling_params)
+for output in completions:
+    gens = output.outputs[0].text
+    print(gens, '\n')
+```