Update README.md

README.md

@@ -62,7 +62,106 @@ MT-Bench-TC
 
 **Dependiency**
 
+Install `mtkresearch` package
+
+```
+git clone https://github.com/mtkresearch/mtkresearch.git
+cd mtkresearch
+pip install -e .
 ```
-pip install mtkresearch vllm
+
+**Hosting by VLLM**
+
+```python
+from vllm import LLM, SamplingParams
+
+llm = LLM(
+    model='MediaTek-Research/Breeze-7B-FC-v1_0',
+    tensor_parallel_size=num_gpu, # number of gpus
+    gpu_memory_utilization=0.7
+)
+
+instance_end_token_id = llm.get_tokenizer().convert_token_to_ids('<|im_end|>')
+params = SamplingParams(
+    temperature=0.01,
+    top_p=0.01,
+    max_tokens=4096,
+    repetition_penalty=1.1,
+    stop_token_ids=[instance_end_token_id]
+)
+
+def _inference(prompt, llm, params):
+    return llm.generate(prompt, params)[0].outputs[0].text
+
+```
+
+**Instruction following**
+
+```python
+from mtkresearch.llm.prompt import MRPromptV2
+
+sys_prompt = 'You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.'
+
+prompt_engine = MRPromptV2()
+
+conversations = [
+    {"role": "system", "content": sys_prompt},
+    {"role": "user", "content": "請問什麼是深度學習？"},
+]
+
+prompt = prompt_engine.get_prompt(conversations)
+
+
+output_str = _inference(prompt, llm, params)
+result = prompt_engine.parse_generated_str(output_str)
+
+print(result) # 
 ```
 
+**Function Calling**
+
+```python
+from mtkresearch.llm.prompt import MRPromptV2
+
+sys_prompt = 'You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.'
+
+functions = [
+    {
+      "name": "get_current_weather",
+      "description": "Get the current weather in a given location",
+      "parameters": {
+        "type": "object",
+        "properties": {
+          "location": {
+            "type": "string",
+            "description": "The city and state, e.g. San Francisco, CA"
+          },
+          "unit": {
+            "type": "string",
+            "enum": ["celsius", "fahrenheit"]
+          }
+        },
+        "required": ["location"]
+      }
+    }
+]
+
+prompt_engine = MRPromptV2()
+
+# stage 1: query
+conversations = [
+    {"role": "user", "content": "台北目前溫度是攝氏幾度？"},
+]
+
+prompt = prompt_engine.get_prompt(conversations, functions=functions)
+
+output_str = _inference(prompt, llm, params)
+result = prompt_engine.parse_generated_str(output_str)
+
+print(result) #
+
+# stage 2: execute called functions
+
+# stage 3: put executed results
+
+```