86 lines
3.4 KiB
Markdown
86 lines
3.4 KiB
Markdown
---
|
|
license: cc-by-nc-nd-4.0
|
|
datasets:
|
|
- kwaikeg/KAgentInstruct
|
|
- kwaikeg/KAgentBench
|
|
language:
|
|
- en
|
|
- zh
|
|
pipeline_tag: text-generation
|
|
---
|
|
|
|
|
|
KwaiAgents ([Github](https://github.com/KwaiKEG/KwaiAgents)) is a series of Agent-related works open-sourced by the [KwaiKEG](https://github.com/KwaiKEG) from [Kuaishou Technology](https://www.kuaishou.com/en). The open-sourced content includes:
|
|
|
|
1. **KAgentSys-Lite**: An experimental Agent Loop implemented based on open-source search engines, browsers, time, calendar, weather, and other tools, which is only missing the memory mechanism and some search capabilities compared to the system in the paper.
|
|
2. **KAgentLMs**: A series of large language models with Agent capabilities such as planning, reflection, and tool-use, acquired through the Meta-agent tuning proposed in the paper.
|
|
3. **KAgentInstruct**: Fine-tuned data of instructions generated by the Meta-agent in the paper.
|
|
4. **KAgentBench**: Over 3,000 human-edited, automated evaluation data for testing Agent capabilities, with evaluation dimensions including planning, tool-use, reflection, concluding, and profiling.
|
|
|
|
|
|
## User Guide
|
|
|
|
### Direct usage
|
|
|
|
Tutorial can refer to [QwenLM/Qwen](https://github.com/QwenLM/Qwen)
|
|
```python
|
|
from modelscope import AutoModelForCausalLM, AutoTokenizer
|
|
from modelscope import GenerationConfig
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained("KwaiKEG/kagentlms_qwen_7b_mat", trust_remote_code=True)
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
"KwaiKEG/kagentlms_qwen_7b_mat",
|
|
device_map="auto",
|
|
trust_remote_code=True
|
|
).eval()
|
|
|
|
response, history = model.chat(tokenizer, "你好", history=None)
|
|
print(response)
|
|
```
|
|
|
|
### AgentLMs as service
|
|
We recommend using [vLLM](https://github.com/vllm-project/vllm) and [FastChat](https://github.com/lm-sys/FastChat) to deploy the model inference service. First, you need to install the corresponding packages (for detailed usage, please refer to the documentation of the two projects):
|
|
```bash
|
|
pip install vllm
|
|
pip install "fschat[model_worker,webui]"
|
|
```
|
|
To deploy KAgentLMs, you first need to start the controller in one terminal.
|
|
```bash
|
|
python -m fastchat.serve.controller
|
|
```
|
|
Secondly, you should use the following command in another terminal for single-gpu inference service deployment:
|
|
```bash
|
|
python -m fastchat.serve.vllm_worker --model-path $model_path --trust-remote-code
|
|
```
|
|
Where `$model_path` is the local path of the model downloaded. If the GPU does not support Bfloat16, you can add `--dtype half` to the command line.
|
|
|
|
Thirdly, start the REST API server in the third terminal.
|
|
```bash
|
|
python -m fastchat.serve.openai_api_server --host localhost --port 8888
|
|
```
|
|
|
|
Finally, you can use the curl command to invoke the model same as the OpenAI calling format. Here's an example:
|
|
```bash
|
|
curl http://localhost:8888/v1/chat/completions \
|
|
-H "Content-Type: application/json" \
|
|
-d '{"model": "kagentlms_qwen_7b_mat", "messages": [{"role": "user", "content": "Who is Andy Lau"}]}'
|
|
```
|
|
|
|
### Citation
|
|
```
|
|
@article{pan2023kwaiagents,
|
|
author = {Haojie Pan and
|
|
Zepeng Zhai and
|
|
Hao Yuan and
|
|
Yaojia Lv and
|
|
Ruiji Fu and
|
|
Ming Liu and
|
|
Zhongyuan Wang and
|
|
Bing Qin
|
|
},
|
|
title = {KwaiAgents: Generalized Information-seeking Agent System with Large Language Models},
|
|
journal = {CoRR},
|
|
volume = {abs/2312.04889},
|
|
year = {2023}
|
|
}
|
|
``` |