Update README.md
Browse files
README.md
CHANGED
|
@@ -1,23 +1,49 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
datasets:
|
| 4 |
-
- magicgh/Ask-before-Plan
|
| 5 |
-
language:
|
| 6 |
-
- en
|
| 7 |
-
base_model:
|
| 8 |
-
- meta-llama/Meta-Llama-3-8B-Instruct
|
| 9 |
-
- mistralai/Mistral-7B-Instruct-v0.2
|
| 10 |
-
---
|
| 11 |
-
|
| 12 |
-
#
|
| 13 |
-
|
| 14 |
-
<
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- magicgh/Ask-before-Plan
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
base_model:
|
| 8 |
+
- meta-llama/Meta-Llama-3-8B-Instruct
|
| 9 |
+
- mistralai/Mistral-7B-Instruct-v0.2
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# CEP Framework
|
| 13 |
+
|
| 14 |
+
<a href="https://arxiv.org/abs/2406.12639">Paper</a> •
|
| 15 |
+
<a href="https://huggingface.co/datasets/magicgh/Ask-before-Plan">Data</a> •
|
| 16 |
+
<a href="https://drive.google.com/file/d/1vMIhs8mpMgk33pFDv2rWg6AJNyD70Sod">Environment</a> •
|
| 17 |
+
<a href="https://github.com/magicgh/Ask-before-Plan">Code</a>
|
| 18 |
+
|
| 19 |
+
This repository contains the checkpoint for the CEP framework in our EMNLP 2024 Paper, *Ask-before-Plan: Proactive Language Agents for Real-World Planning*.
|
| 20 |
+
We release our CEP models, including LLaMA-3-8B and Mistral-7B variants, finetuned on Clarification and Execution subtasks.
|
| 21 |
+
|
| 22 |
+
## Get Started
|
| 23 |
+
1. Download our checkpoints.
|
| 24 |
+
```bash
|
| 25 |
+
git lfs install
|
| 26 |
+
git clone https://huggingface.co/magicgh/CEP
|
| 27 |
+
```
|
| 28 |
+
2. OpenAI compatible servers.
|
| 29 |
+
```bash
|
| 30 |
+
python3 -m vllm.entrypoints.openai.api_server
|
| 31 |
+
--served-model-name ${model_name}
|
| 32 |
+
--model ${model}
|
| 33 |
+
--kv-cache-dtype fp8
|
| 34 |
+
--port ${port}
|
| 35 |
+
--enable-lora
|
| 36 |
+
--lora-modules ${lora_models}
|
| 37 |
+
--chat-template ${chat_template}
|
| 38 |
+
```
|
| 39 |
+
## Citation
|
| 40 |
+
If you find our research helpful for your work, please star [this repository](https://github.com/magicgh/Ask-before-Plan) and cite our paper:
|
| 41 |
+
```
|
| 42 |
+
@article{ask-before-plan,
|
| 43 |
+
author = {Xuan Zhang and Yang Deng and Zifeng Ren and See-Kiong Ng and Tat-Seng Chua},
|
| 44 |
+
journal = {ArXiv preprint},
|
| 45 |
+
title = {Ask-before-Plan: Proactive Language Agents for Real-World Planning},
|
| 46 |
+
url = {https://arxiv.org/abs/2406.12639},
|
| 47 |
+
year = {2024}
|
| 48 |
+
}
|
| 49 |
+
```
|