katanemo/Arch-Function-1.5B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Upload folder using huggingface_hub

Browse Source
This commit is contained in:
ai-modelscope
2025-01-04 11:47:47 +08:00
parent 371090cfef
commit 2fd8d75513
11 changed files with 455356 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

380
README.md
View File

@@ -1,47 +1,345 @@
---
license: Apache License 2.0
#model-type:
##如 gpt、phi、llama、chatglm、baichuan 等
#- gpt
#domain:
##如 nlp、cv、audio、multi-modal
#- nlp
#language:
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
#- cn
#metrics:
##如 CIDEr、Blue、ROUGE 等
#- CIDEr
#tags:
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
#- pretrained
#tools:
##如 vllm、fastchat、llamacpp、AdaSeq 等
#- vllm
license: other
license_name: katanemo-research
license_link: >-
https://huggingface.co/katanemolabs/Arch-Function-1.5B/blob/main/LICENSE
base_model:
- Qwen/Qwen2.5-Coder-1.5B-Instruct
language:
- en
pipeline_tag: text-generation
library_name: transformers
---
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
SDK下载
# katanemo/Arch-Function-1.5B
## Overview
The Katanemo Arch-Function collection of large language models (LLMs) is a collection state-of-the-art (SOTA) LLMs specifically designed for **function calling** tasks. The models are designed to understand complex function signatures, identify required parameters, and produce accurate function call outputs based on natural language prompts. Achieving performance on par with GPT-4, these models set a new benchmark in the domain of function-oriented tasks, making them suitable for scenarios where automated API interaction and function execution is crucial.
In summary, the Katanemo Arch-Function collection demonstrates:
- **State-of-the-art performance** in function calling
- **Accurate parameter identification and suggestion**, even in ambiguous or incomplete inputs
- **High generalization** across multiple function calling use cases, from API interactions to automated backend tasks.
- Optimized **low-latency, high-throughput** performance, making it suitable for real-time, production environments.
Arch-Function is the core LLM used in then open source [Arch Gateway](https://github.com/katanemo/arch) to seamlessly integrate user prompts with developers APIs
## Key Features
<table>
<tr style="text-align: left; vertical-align: middle; font-weight: bold;">
<td>Functionality</td>
<td>Definition</td>
</tr>
<tr style="text-left: left; vertical-align: middle;">
<td>Single Function Calling</td>
<td>Call only one function per user query </td>
</tr>
<tr style="text-left: left; vertical-align: middle;">
<td>Parallel Function Calling</td>
<td>Call the same function multiple times but with different set of parameter values</td>
</tr>
<tr style="text-left: left; vertical-align: middle;">
<td>Multiple Function Calling</td>
<td>Call different functions per user query</td>
</tr>
<tr style="text-left: left; vertical-align: middle;">
<td>Parallel & Multiple</td>
<td>Perform both parallel and multiple function calling</td>
</tr>
</table>
## Training Details
Katanemo Arch-Function collection is built on top of the [Qwen 2.5](https://huggingface.co/collections/Qwen/qwen25-66e81a666513e518adb90d9e). A blog with technical details leading to our models will be published soon.
## Performance Benchmarks
We evaluate Katanemo Arch-Function series on the [Berkeley Function-Calling Leaderboard (BFCL)](https://gorilla.cs.berkeley.edu/leaderboard.html#leaderboard). We compare with commonly-used models and the results (as of Oct 21st, 2024) are shwon below. For each model family, we select the one with the highest rank.
<table>
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
<td rowspan=2>Rank</td>
<td rowspan=2>Model</td>
<td rowspan=2>Overall</td>
<td colspan=3>Single Turn</td>
<td rowspan=1>Multi Turn</td>
<td colspan=2>Hallucination</td>
</tr>
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
<td>Non-live (AST)</td>
<td>Non-live (Exec)</td>
<td>Live (AST)</td>
<td>Overall</td>
<td>Relevance</td>
<td>Irrelevance</td>
</tr>
<tr style="text-align: center; vertical-align: middle;">
<td>1</td>
<td>GPT-4o-2024-08-06 (FC)</td>
<td>62.19%</td>
<td>85.90%</td>
<td>85.64%</td>
<td>75.43%</td>
<td>25.00%</td>
<td>63.41%</td>
<td>82.93%</td>
</tr>
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
<td> </td>
<td>Arch-Function-7B</td>
<td>59.62%</td>
<td>86.83%</td>
<td>88.07%</td>
<td>71.57%</td>
<td>21.00%</td>
<td>95.12%</td>
<td>73.63%</td>
</tr>
<tr style="text-align: center; vertical-align: middle;">
<td>6</td>
<td>o1-preview-2024-09-12 (Prompt)</td>
<td>59.27%</td>
<td>86.42%</td>
<td>88.88%</td>
<td>73.08%</td>
<td>17.62%</td>
<td>73.17%</td>
<td>74.60%</td>
</tr>
<tr style="text-align: center; vertical-align: middle; ">
<td>9</td>
<td>Gemini-1.5-Flash-002 (Prompt)</td>
<td>57.92%</td>
<td>86.58%</td>
<td>89.48%</td>
<td>76.28%</td>
<td>9.88%</td>
<td>85.37%</td>
<td>78.54%</td>
</tr>
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
<td> </td>
<td>Arch-Function-3B</td>
<td>57.69%</td>
<td>85.19%</td>
<td>86.18%</td>
<td>71.21%</td>
<td>17.50%</td>
<td>90.24%</td>
<td>72.88%</td>
</tr>
<tr style="text-align: center; vertical-align: middle; ">
<td>12</td>
<td>Claude-3.5-Sonnet-20240620 (FC)</td>
<td>57.42%</td>
<td>70.04%</td>
<td>66.27%</td>
<td>74.68%</td>
<td>28.38%</td>
<td>68.29%</td>
<td>74.58%</td>
</tr>
<tr style="text-align: center; vertical-align: middle; ">
<td>13</td>
<td>mistral-large-2407 (FC)</td>
<td>56.80%</td>
<td>86.62%</td>
<td>84.57%</td>
<td>68.37%</td>
<td>20.62%</td>
<td>75.61%</td>
<td>49.44%</td>
</tr>
<tr style="text-align: center; vertical-align: middle; font-weight: bold;">
<td> </td>
<td>Arch-Function-1.5B</td>
<td>56.20%</td>
<td>84.40%</td>
<td>83.96%</td>
<td>69.36%</td>
<td>15.88%</td>
<td>87.80%</td>
<td>74.39%</td>
</tr>
<tr style="text-align: center; vertical-align: middle; ">
<td>21</td>
<td>Llama-3.1-70B-Instruct (Prompt)</td>
<td>53.67%</td>
<td>88.90%</td>
<td>89.34%</td>
<td>61.13%</td>
<td>12.38%</td>
<td>92.68%</td>
<td>58.38%</td>
</tr>
<tr style="text-align: center; vertical-align: middle; ">
<td>22</td>
<td>Gemma-2-27b-it (Prompt)</td>
<td>53.66%</td>
<td>88.52%</td>
<td>87.89%</td>
<td>69.48%</td>
<td>4.12%</td>
<td>87.8%</td>
<td>68.76%</td>
</tr>
</table>
# Requirements
The code of Arch-Function-1.5B has been in the Hugging Face `transformers` library and we advise you to install latest version:
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('katanemo/Arch-Function-1.5B')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/katanemo/Arch-Function-1.5B.git
pip install transformers>=4.37.0
```
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
# How to use
We use the following example to illustrate how to use our model to perform function calling tasks. Please note that, our model works best with our provided prompt format. It allows us to extract JSON output that is similar to the [function-calling mode of ChatGPT](https://platform.openai.com/docs/guides/function-calling).
### Single Turn Example
````python
import json
from typing import Any, Dict, List
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "katanemo/Arch-Function-1.5B"
model = AutoModelForCausalLM.from_pretrained(
model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
# Please use our provided prompt for best performance
TASK_PROMPT = """
You are a helpful assistant.
""".strip()
TOOL_PROMPT = """
# Tools
You may call one or more functions to assist with the user query.
You are provided with function signatures within <tools></tools> XML tags:
<tools>
{tool_text}
</tools>
""".strip()
FORMAT_PROMPT = """
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
<tool_call>
{"name": <function-name>, "arguments": <args-json-object>}
</tool_call>
""".strip()
# Define available tools
get_weather_api = {
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "str",
"description": "The city and state, e.g. San Francisco, New York",
},
"unit": {
"type": "str",
"enum": ["celsius", "fahrenheit"],
"description": "The unit of temperature to return",
},
},
"required": ["location"],
},
},
}
openai_format_tools = [get_weather_api]
def convert_tools(tools: List[Dict[str, Any]]):
return "\n".join([json.dumps(tool) for tool in tools])
# Helper function to create the system prompt for our model
def format_prompt(tools: List[Dict[str, Any]]):
tool_text = convert_tools(tools)
return (
TASK_PROMPT
+ "\n\n"
+ TOOL_PROMPT.format(tool_text=tool_text)
+ "\n\n"
+ FORMAT_PROMPT
+ "\n"
)
system_prompt = format_prompt(openai_format_tools)
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": "What is the weather in Seattle?"},
]
inputs = tokenizer.apply_chat_template(
messages, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
outputs = model.generate(
inputs,
max_new_tokens=512,
do_sample=False,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
response = tokenizer.decode(outputs[0][len(inputs[0]) :], skip_special_tokens=True)
print(response)
````
Then you should be able to see the following output string in JSON format:
````python
<tool_call>
{"name": "get_weather", "arguments": {"location": "Seattle"}}
</tool_call>
````
### Multi Turn Example
Upon getting results from functions, you can add it to the `messages` list as a `user` message and pass it to the model to get responses for users.
````python
# Suppose we receive the following result from the function:
get_weather_api_result = {'name': 'get_weather', 'results': {'temperature': '62°', 'unit': 'fahrenheit'}}
execution_results = [get_weather_api_result]
def add_execution_results(messages: List[Dict[str, Any]], execution_results: List[Dict[str, Any]]):
content = "\n".join([f"<tool_response>\n{json.dumps(result)}</tool_response>" for result in execution_results])
messages.append({"role": "user", "content": content})
return messages
messages = add_execution_results(messages, execution_results)
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(
inputs,
max_new_tokens=512,
do_sample=False,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
)
response = tokenizer.decode(outputs[0][len(inputs[0]) :], skip_special_tokens=True)
print(response)
````
Then you should be able to see the following output:
```
The current temperature in Seattle is 62 degrees in Fahrenheit.
```
# License
Katanemo Arch-Function collection is distributed under the [Katanemo license](https://huggingface.co/katanemolabs/Arch-Function-1.5B/blob/main/LICENSE).