add guidance

README.md

@@ -1,3 +1,113 @@
 ---
 license: apache-2.0
+tags:
+- qwen1.5
+- function-calling
+- zero-shot
 ---
+# Qwen1.5 one shot chat template for function calling
+
+This repo contains a tokenizer with a custom chat template in the tokenizer_config.json file.
+
+The custom chat template can be used - via 'tokenizer.apply_chat_template' - to format an array of messages.
+
+For example:
+```
+function_metadata = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_current_weather",
+            "description": "This function gets the current weather in a given city",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "city": {
+                        "type": "string",
+                        "description": "The city, e.g., San Francisco"
+                    },
+                    "format": {
+                        "type": "string",
+                        "enum": ["celsius", "fahrenheit"],
+                        "description": "The temperature unit to use."
+                    }
+                },
+                "required": ["city"]
+            }
+        }
+    },
+    {
+        "type": "function",
+        "function": {
+            "name": "get_clothes",
+            "description": "This function provides a suggestion of clothes to wear based on the current weather",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "temperature": {
+                        "type": "string",
+                        "description": "The temperature, e.g., 15 C or 59 F"
+                    },
+                    "condition": {
+                        "type": "string",
+                        "description": "The weather condition, e.g., 'Cloudy', 'Sunny', 'Rainy'"
+                    }
+                },
+                "required": ["temperature", "condition"]
+            }
+        }
+    }    
+]
+
+# Comment out later messages to test various stages of generation.
+
+sample_messages = [
+    # System messages are not supported by default
+    # {
+    #     "role": "system",
+    #     "content": "you are a helpful assistant"
+    # },
+    {
+        "role": "function_metadata",
+        "content": "FUNCTION_METADATA"
+    },
+    {
+        "role": "user",
+        "content": "What is the current weather in London?"
+    },
+    # {
+    #     "role": "function_call",
+    #     "content": "{\n    \"name\": \"get_current_weather\",\n    \"arguments\": {\n        \"city\": \"London\"\n    }\n}"
+    # },
+    # {
+    #     "role": "function_response",
+    #     "content": "{\n    \"temperature\": \"15 C\",\n    \"condition\": \"Cloudy\"\n}"
+    # },
+    # {
+    #     "role": "assistant",
+    #     "content": "The current weather in London is Cloudy with a temperature of 15 Celsius.<|end_of_turn|>"
+    # },
+    # {
+    #     "role": "user",
+    #     "content": "That's great. Now say hello."
+    # },
+    # {
+    #     "role": "assistant",
+    #     "content": "Hello!"
+    # }
+]
+
+# Iterate through each message in the list
+for message in sample_messages:
+    if message['role'] == 'function_metadata':
+        # Replace 'FUNCTION_METADATA' with 'function_metadata' in the content
+        message['content'] = message['content'].replace('FUNCTION_METADATA', json.dumps(function_metadata, indent=4))
+
+# View the template applied without tokenization
+prompt = tokenizer.apply_chat_template(sample_messages, tokenize=False, add_generation_prompt=True)
+print(prompt)
+```
+
+This will provide a prompt format for doing zero-shot function calling, for example using a TGI api.
+
+Alternatively, when deploying a vLLM endpoint, this repo id may be passed as the tokenizer for a Qwen1.5 chat model, and the chat template will be applied. In this case, you simply need to prepare your array of messages as per above.