Add Qwen handler and fix mean_latency calculation error for OSS models (#642)

Hello, there may be an anomaly in the mean latency calculation of the
OSS model, and I have attempted to fix it.

---------

Co-authored-by: ai_user <[email protected]>
Co-authored-by: Huanzhi (Hans) Mao <[email protected]>

Author: 3 people

berkeley-function-call-leaderboard/CHANGELOG.md

@@ -2,6 +2,11 @@
 
 All notable changes to the Berkeley Function Calling Leaderboard will be documented in this file.
 
+- [Oct 5, 2024] [#642](https://github.com/ShishirPatil/gorilla/pull/642): Add the following new models to the leaderboard:
+  - `Qwen/Qwen2.5-7B-Instruct`
+  - `Qwen/Qwen2.5-1.5B-Instruct`
+  - `Qwen/Qwen2-7B-Instruct`
+  - `Qwen/Qwen2-1.5B-Instruct`
 - [Oct 4, 2024] [#653](https://github.com/ShishirPatil/gorilla/pull/653): Add new model `Team-ACE/ToolACE-8B` to the leaderboard.
 - [Oct 4, 2024] [#671](https://github.com/ShishirPatil/gorilla/pull/671): Speed up locally-hosted model's inference process by parallelizing the inference requests.
 - [Sept 27, 2024] [#640](https://github.com/ShishirPatil/gorilla/pull/640): Add the following new models to the leaderboard:

berkeley-function-call-leaderboard/README.md

@@ -186,6 +186,8 @@ Below is _a table of models we support_ to run our leaderboard evaluation agains
 |ibm-granite/granite-20b-functioncalling 💻| Function Calling|
 |yi-large-fc | Function Calling|
 |MadeAgents/Hammer-7b 💻| Function Calling|
+|Qwen/Qwen2.5-{1.5B,7B}-Instruct 💻| Prompt|
+|Qwen/Qwen2-{1.5B,7B}-Instruct 💻| Prompt|
 |Team-ACE/ToolACE-8B 💻| Function Calling|
 
 Here {MODEL} 💻 means the model needs to be hosted locally and called by vllm, {MODEL} means the models that are called API calls. For models with a trailing `-FC`, it means that the model supports function-calling feature. You can check out the table summarizing feature supports among different models [here](https://gorilla.cs.berkeley.edu/blogs/8_berkeley_function_calling_leaderboard.html#prompt).

berkeley-function-call-leaderboard/bfcl/eval_checker/model_metadata.py

@@ -581,6 +581,30 @@
         "Microsoft",
         "MIT",
     ],
+    "Qwen/Qwen2-1.5B-Instruct": [
+        "Qwen2-1.5B-Instruct (Prompt)",
+        "https://huggingface.co/Qwen/Qwen2-1.5B-Instruct",
+        "Qwen",
+        "apache-2.0",
+    ],
+    "Qwen/Qwen2-7B-Instruct": [
+        "Qwen2-7B-Instruct (Prompt)",
+        "https://huggingface.co/Qwen/Qwen2-7B-Instruct",
+        "Qwen",
+        "apache-2.0",
+    ],
+    "Qwen/Qwen2.5-1.5B-Instruct": [
+        "Qwen2.5-1.5B-Instruct (Prompt)",
+        "https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct",
+        "Qwen",
+        "apache-2.0",
+    ],
+    "Qwen/Qwen2.5-7B-Instruct": [
+        "Qwen2.5-7B-Instruct (Prompt)",
+        "https://huggingface.co/Qwen/Qwen2.5-7B-Instruct",
+        "Qwen",
+        "apache-2.0",
+    ],
     "Team-ACE/ToolACE-8B": [
         "ToolACE-8B (FC)",
         "https://huggingface.co/Team-ACE/ToolACE-8B",

berkeley-function-call-leaderboard/bfcl/model_handler/handler_map.py

@@ -9,6 +9,7 @@
 from bfcl.model_handler.oss_model.llama_fc import LlamaFCHandler
 from bfcl.model_handler.oss_model.phi import PhiHandler
 from bfcl.model_handler.oss_model.salesforce import SalesforceHandler
+from bfcl.model_handler.oss_model.qwen import QwenHandler
 from bfcl.model_handler.proprietary_model.claude import ClaudeHandler
 from bfcl.model_handler.proprietary_model.cohere import CohereHandler
 from bfcl.model_handler.proprietary_model.databricks import DatabricksHandler
@@ -108,6 +109,10 @@
     "ibm-granite/granite-20b-functioncalling": GraniteHandler,
     # "MadeAgents/Hammer-7b": HammerHandler,  # TODO: Update handler once they have a multi-turn format
     "THUDM/glm-4-9b-chat": GLMHandler,
+    "Qwen/Qwen2-1.5B-Instruct": QwenHandler,
+    "Qwen/Qwen2-7B-Instruct": QwenHandler,
+    "Qwen/Qwen2.5-1.5B-Instruct": QwenHandler,
+    "Qwen/Qwen2.5-7B-Instruct": QwenHandler,
     "Team-ACE/ToolACE-8B": LlamaHandler,
 
     # Deprecated/outdated models, no longer on the leaderboard

berkeley-function-call-leaderboard/bfcl/model_handler/oss_model/qwen.py

@@ -0,0 +1,20 @@
+from bfcl.model_handler.oss_model.base_oss_handler import OSSHandler
+
+
+class QwenHandler(OSSHandler):
+    def __init__(self, model_name, temperature) -> None:
+        super().__init__(model_name, temperature)
+
+    def _format_prompt(self, messages, function):
+        # Qwen is using its prompting mode, not the tool use mode
+        """
+        "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+        """
+        formatted_prompt = ""
+
+        for message in messages:
+            formatted_prompt += f"<|im_start|>{message['role']}\n{message['content']}<|im_end|>\n"
+
+        formatted_prompt += "<|im_start|>assistant\n"
+
+        return formatted_prompt