---
license: cc-by-nc-nd-4.0
datasets:
- kwaikeg/KAgentInstruct
- kwaikeg/KAgentBench
language:
- en
- zh
pipeline_tag: text2text-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 [baichuan-inc/Baichuan2-13B-Base](https://github.com/baichuan-inc/Baichuan2)
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/Baichuan2-13B-Base", use_fast=False, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("baichuan-inc/Baichuan2-13B-Base", device_map="auto", trust_remote_code=True)
inputs = tokenizer('登鹳雀楼->王之涣\n夜雨寄北->', return_tensors='pt')
inputs = inputs.to('cuda:0')
pred = model.generate(**inputs, max_new_tokens=64, repetition_penalty=1.1)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
```

### 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 "fschat[model_worker,webui]"
pip install vllm==0.2.0
pip install transformers==4.33.2
```
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_baichuan2_13b_mat", "messages": [{"role": "user", "content": "Who is Andy Lau"}]}'
```