Release training script

Former-commit-id: 88e5ed3291935fe5dafe719fbd6b6b31a9c68216

README.md

@@ -2,7 +2,7 @@
 
 <font size=7><div align='center'><b>LISA</b>: Large <b>L</b>anguage <b>I</b>nstructed <b>S</b>egmentation <b>A</b>ssistant</div></font>
 
-<font size=7><div align='center' > <a href=https://arxiv.org/pdf/2308.00692.pdf>**Paper**</a> | <a href="https://huggingface.co/xinlai">**Models**</a> | **Training** (Coming Soon) | [**Inference**](#inference) | [**Dataset**](#dataset) | <a href="http://103.170.5.190:7860/">**Online Demo**</a></div></font>
+<font size=7><div align='center' > <a href=https://arxiv.org/pdf/2308.00692.pdf>**Paper**</a> | <a href="https://huggingface.co/xinlai">**Models**</a> | [Training](#training) | [**Inference**](#inference) | [**Dataset**](#dataset) | <a href="http://103.170.5.190:7860/">**Online Demo**</a></div></font>
 
 <!-- <p align="center"> <img src="imgs/teaser.jpg" width="100%"> </p> -->
 
@@ -69,14 +69,12 @@
 <p align="center"> <img src="imgs/fig_overview.jpg" width="100%"> </p>
 
 ## News
+- [x] [2023.8.9] Training Code Release
 - [x] [2023.8.4] [Online Demo](http://103.170.5.190:7860/) is released! 
 - [x] [2023.8.4] [*ReasonSeg* Dataset](https://drive.google.com/drive/folders/125mewyg5Ao6tZ3ZdJ-1-E3n04LGVELqy?usp=sharing) and the [LISA-13B-llama2-v0-explanatory](https://huggingface.co/xinlai/LISA-13B-llama2-v0-explanatory) model are released! 
 - [x] [2023.8.3] Inference code and the [LISA-13B-llama2-v0](https://huggingface.co/xinlai/LISA-13B-llama2-v0) model are released. Welcome to check out!
 - [x] [2023.8.2] [Paper](https://arxiv.org/pdf/2308.00692.pdf) is released and GitHub repo is created.
 
-## TODO 
-- [ ] Training Code Release
-
 **LISA: Reasoning Segmentation Via Large Language Model [[Paper](https://arxiv.org/abs/2308.00692)]** <br />
 [Xin Lai](https://scholar.google.com/citations?user=tqNDPA4AAAAJ&hl=zh-CN),
 [Zhuotao Tian](https://scholar.google.com/citations?user=mEjhz-IAAAAJ&hl=en),

model/LISA.py

@@ -6,7 +6,7 @@ import torch.nn.functional as F
 from peft import (LoraConfig, get_peft_model)
 from transformers import BitsAndBytesConfig, CLIPVisionModel
 
-from transformers import LlamaForCausalLM, CLIPVisionModel, BitsAndBytesConfig
+from transformers import CLIPVisionModel, BitsAndBytesConfig
 from .llava.model.llava import LlavaLlamaForCausalLM
 from .segment_anything import build_sam_vit_h
 from utils.utils import (DEFAULT_IM_END_TOKEN, DEFAULT_IM_START_TOKEN,