Hugging Face's logo

openbmb
/
MiniCPM-V-4_5-int4

Image-Text-to-Text
Transformers
Safetensors
multilingual
minicpm-v
vision
ocr
multi-image
video
custom_code
8-bit precision
Model card Files
xet
 Community
3

comfyui

#2
by taom - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+1
-2
Files changed (2) hide show
  1. README.md +1 -1
  2. modeling_minicpmv.py +0 -1
README.md CHANGED
@@ -17,7 +17,7 @@ license: apache-2.0
17
 
18
  <h1>A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone</h1>
19
 
20
- [GitHub](https://github.com/OpenBMB/MiniCPM-o) | [CookBook](https://github.com/OpenSQZ/MiniCPM-V-CookBook) | [Technical Report](https://huggingface.co/papers/2509.18154) | [Demo](http://211.93.21.133:18120/) </a>
21
 
22
 
23
 
 
17
 
18
  <h1>A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone</h1>
19
 
20
+ [GitHub](https://github.com/OpenBMB/MiniCPM-o) | [CookBook](https://github.com/OpenSQZ/MiniCPM-V-CookBook) | [Technical Report](https://huggingface.co/papers/2509.18154) | [Demo](http://101.126.42.235:30910/) </a>
21
 
22
 
23
 
modeling_minicpmv.py CHANGED
@@ -30,7 +30,6 @@ class MiniCPMV(MiniCPMVPreTrainedModel):
30
  self.processor = None
31
 
32
  self.terminators = ['<|im_end|>', '<|endoftext|>']
33
- self.post_init()
34
 
35
  def init_vision_module(self):
36
  # same as HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit add tgt_sizes
 
30
  self.processor = None
31
 
32
  self.terminators = ['<|im_end|>', '<|endoftext|>']
 
33
 
34
  def init_vision_module(self):
35
  # same as HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit add tgt_sizes