new version of pre-trained model!

Q-Future · Dec 13, 2023 · 4a163b8 · 4a163b8
1 parent 19e7d53
commit 4a163b8
Show file tree

Hide file tree

Showing 4 changed files with 6 additions and 5 deletions.
diff --git a/README.md b/README.md
@@ -166,7 +166,7 @@ pip install -e .
 ```python
 from mplug_owl2.mm_utils import get_model_name_from_path
 from eval_scripts.mplug_owl_2.run_mplug_owl2 import eval_model
-model_path = "teowu/mplug_owl2_7b_448_qinstruct_preview_v0.1" 
+model_path = "teowu/mplug_owl2_7b_448_qinstruct_preview_v0.2" 
 prompt = "Rate the quality of the image. Think step by step."
 image_file = "fig/sausage.jpg"
 args = type('Args', (), {

diff --git a/model_zoo/README.md b/model_zoo/README.md
@@ -10,7 +10,8 @@ _Released_:
 
 - [LLaVA-v1.5-7B (mix)](https://huggingface.co/teowu/llava_v1.5_7b_qinstruct_preview_v0.1), HF-path: `teowu/llava_v1.5_7b_qinstruct_preview_v0.1`
 - [LLaVA-v1.5-13B (mix)](https://huggingface.co/teowu/llava_v1.5_13b_qinstruct_preview_v0.1), HF-path: `teowu/llava_v1.5_13b_qinstruct_preview_v0.1`
-- [mPLUG-Owl-2 (mix)](https://huggingface.co/teowu/mplug_owl2_7b_448_qinstruct_preview_v0.1), HF-path: `teowu/mplug_owl2_7b_448_qinstruct_preview_v0.1`
+- [mPLUG-Owl-2 (mix, new version)](https://huggingface.co/teowu/mplug_owl2_7b_448_qinstruct_preview_v0.2), HF-path: `teowu/mplug_owl2_7b_448_qinstruct_preview_v0.2` (improves 2-3% on Q-Bench-MCQ)
+- [mPLUG-Owl-2 (mix, old version)](https://huggingface.co/teowu/mplug_owl2_7b_448_qinstruct_preview_v0.1), HF-path: `teowu/mplug_owl2_7b_448_qinstruct_preview_v0.1`
 - [InternLM-XComposer-VL (mix)](https://huggingface.co/DLight1551/internlm-xcomposer-vl-7b-qinstruct-full), HF-path: `DLight1551/internlm-xcomposer-vl-7b-qinstruct-full`
 
 

diff --git a/scripts/llava_v1.5/README.md b/scripts/llava_v1.5/README.md
@@ -1,4 +1,4 @@
-## Training@LLaVA-v1.5
+## Train@LLaVA-v1.5
 
 This document provides instruction on how to train with **Q-Instruct** dataset on LLaVA-v1.5 (7B/13B), under the proposed two strategies (***mix*** and ***after***), shown as follows.
 

diff --git a/scripts/mplug_owl_2/README.md b/scripts/mplug_owl_2/README.md
@@ -1,4 +1,4 @@
-## Training@mPLUG-Owl-2
+## Train@mPLUG-Owl-2
 
 This document provides instruction on how to train with **Q-Instruct** dataset on mPLUG-Owl-2 (LLaMA2-7B), under the proposed two strategies (***mix*** and ***after***), shown as follows.
 
@@ -114,4 +114,4 @@ sh scripts/mplug_owl_2/mix_qinstruct.sh
 
 ```shell
 sh scripts/mplug_owl_2/after_qinstruct.sh
-```PLUG-Owl/mPLUG_Owl2/playground/data/mix_cleaned_labels.json
+```