Upload model files
Browse files- README.md +31 -2
- config.json +1 -1
- model-00001-of-00004.safetensors +2 -2
- model-00002-of-00004.safetensors +2 -2
- model-00003-of-00004.safetensors +2 -2
- model-00004-of-00004.safetensors +2 -2
- model.safetensors.index.json +0 -0
README.md
CHANGED
|
@@ -28,6 +28,35 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
| 28 |
import torch
|
| 29 |
|
| 30 |
# load model
|
| 31 |
-
model =
|
| 32 |
-
tokenizer =
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
```
|
|
|
|
| 28 |
import torch
|
| 29 |
|
| 30 |
# load model
|
| 31 |
+
model = Qwen2_5_VLForConditionalGeneration.from_pretrained("Ricky06662/Seg-Zero-7B")
|
| 32 |
+
tokenizer = Qwen2_5_VLForConditionalGeneration.from_pretrained("Ricky06662/Seg-Zero-7B")
|
| 33 |
+
```
|
| 34 |
+
|
| 35 |
+
## Installation
|
| 36 |
+
|
| 37 |
+
```bash
|
| 38 |
+
git clone https://github.com/dvlab-research/Seg-Zero.git
|
| 39 |
+
cd Seg-Zero
|
| 40 |
+
conda create -n seg_zero python=3.11
|
| 41 |
+
conda activate seg_zero
|
| 42 |
+
pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1
|
| 43 |
+
pip install -e .
|
| 44 |
+
pip install sam2
|
| 45 |
+
pip install matplotlib
|
| 46 |
+
```
|
| 47 |
+
|
| 48 |
+
## Inference
|
| 49 |
+
|
| 50 |
+
```bash
|
| 51 |
+
python inference_scripts/infer.py
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
The default question is:
|
| 55 |
+
|
| 56 |
+
> "the unusual object in the image."
|
| 57 |
+
|
| 58 |
+
You will get the thinking process in the command line and the mask will be saved in the **inference_scripts** folder. You can also provide your own image_path and text:
|
| 59 |
+
|
| 60 |
+
```bash
|
| 61 |
+
python inference_scripts/infer.py --image_path "your_image_path" --text "your question text"
|
| 62 |
```
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/gpfs/yuqiliu/easyr1_workdir/
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2_5_VLForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/gpfs/yuqiliu/easyr1_workdir/22_run_qwen2_5_vl_7b_refcocog_add_boxl1_kl1e-2_lr1e-6_strict_format_n8/global_step_562/actor/huggingface",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2_5_VLForConditionalGeneration"
|
| 5 |
],
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38c48425cee36ddfd4fbbc0b2993f36f06fa4ac8e460c1b79be0b59efc953fdd
|
| 3 |
+
size 4888372856
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:139ba86b1b9750588060df19471bbcaf4735933e90e98c0433bd7d965397f591
|
| 3 |
+
size 4930885376
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d2fd346eb88c8164a9c4c34fef43aa15d9b913ae1f21d2c1d408ccd487fa992
|
| 3 |
+
size 4490074192
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d33376846110acadfe1735ebd6309a20235a365289a2b599b75a37c9d2a51ef
|
| 3 |
+
size 2275082104
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|