yuhos16 commited on
Commit
dae35d7
·
verified ·
1 Parent(s): bc5cccc

Upload requirements.txt with huggingface_hub

Browse files
Files changed (1) hide show
  1. requirements.txt +26 -0
requirements.txt ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Base requirements
2
+ torch==2.4.0
3
+ torchvision==0.19.0
4
+ accelerate>=0.26.0
5
+
6
+ # Model specific utilities
7
+ qwen-vl-utils==0.0.10
8
+ transformers-stream-generator==0.0.4
9
+ av
10
+ pillow>=10.0.0
11
+
12
+ # API & Serving (New: For FastAPI deployment)
13
+ fastapi>=0.100.0
14
+ uvicorn>=0.20.0
15
+ python-multipart>=0.0.6
16
+ openai>=1.0.0 # For DeepSeek API (OpenAI-compatible)
17
+
18
+ # Install latest transformers from source (Required for Qwen2.5-VL/Vision-R1)
19
+ git+https://github.com/huggingface/transformers.git
20
+
21
+ # Optional but recommended for GPU acceleration
22
+ # flash-attn==2.6.1
23
+
24
+ # For potential future demo usage
25
+ gradio==5.4.0
26
+ gradio_client==1.4.2