luodian Haozhangcx commited on
Commit
bc4567f
1 Parent(s): 56d001a

Update README.md (#3)

Browse files

- Update README.md (2214d5b1c85b33097a870b520631badcd6b18643)


Co-authored-by: Hao Zhang <Haozhangcx@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +13 -3
README.md CHANGED
@@ -14,7 +14,7 @@ Base LLM: Qwen/Qwen1.5-7B-Chat
14
 
15
  ### Model Description
16
 
17
- **Repository:** https://github.com/...
18
 
19
  **Primary intended uses:** The primary use of LLaVA-Next Interleave is research on large multimodal models and chatbots. This is only for research exploration, and prohibited for commercial usage.
20
 
@@ -28,7 +28,14 @@ This project utilizes certain datasets and checkpoints that are subject to their
28
 
29
  Use the code below to get started with the model.
30
 
31
- [More Information Needed]
 
 
 
 
 
 
 
32
 
33
 
34
 
@@ -36,4 +43,7 @@ Use the code below to get started with the model.
36
 
37
  Use the code below to evaluate the model.
38
 
39
- [More Information Needed]
 
 
 
 
14
 
15
  ### Model Description
16
 
17
+ **Repository:** https://github.com/LLaVA-VL/LLaVA-NeXT
18
 
19
  **Primary intended uses:** The primary use of LLaVA-Next Interleave is research on large multimodal models and chatbots. This is only for research exploration, and prohibited for commercial usage.
20
 
 
28
 
29
  Use the code below to get started with the model.
30
 
31
+ ```bash
32
+ git clone https://github.com/LLaVA-VL/LLaVA-NeXT
33
+ # install llava-next
34
+ ...
35
+ # download the ckpt
36
+ ...
37
+ bash playground/demo/interleave_demo.py --model_path path/to/ckpt
38
+ ```
39
 
40
 
41
 
 
43
 
44
  Use the code below to evaluate the model.
45
 
46
+ Please first edit /path/to/ckpt to the path of checkpoint, /path/to/images to the path of "interleave_data" in scripts/interleave/eval_all.sh and then run
47
+ ```bash
48
+ bash scripts/interleave/eval_all.sh
49
+ ```