Hugging Face's logo

numind
/
NuExtract-2.0-8B

Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
image-to-text
conversational
text-generation-inference
Model card Files
xet
Community
7
liamcripwell commited on
Commit
f59852e
·
verified ·
1 Parent(s): 640dfb3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -2
README.md CHANGED
@@ -2,10 +2,17 @@
2
  library_name: transformers
3
  license: mit
4
  base_model:
5
- - Qwen/Qwen2.5-VL-3B-Instruct
6
  pipeline_tag: image-text-to-text
7
  ---
8
 
 
 
 
 
 
 
 
9
  # NuExtract 2.0 8B by NuMind 📈📈📈
10
 
11
  NuExtract 2.0 is a family of models trained specifically for structured information extraction tasks. It supports both multimodal inputs and is multilingual.
@@ -14,7 +21,7 @@ We provide several versions of different sizes, all based on pre-trained models
14
  | Model Size | Model Name | Base Model | License | Huggingface Link |
15
  |------------|------------|------------|---------|------------------|
16
  | 2B | NuExtract-2.0-2B | [Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) | MIT | 🤗 [NuExtract-2.0-2B](https://huggingface.co/numind/NuExtract-2.0-2B) |
17
- | 3B | NuExtract-2.0-3B | [Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) | Qwen Research License | 🤗 [NuExtract-2.0-3B](https://huggingface.co/numind/NuExtract-2.0-3B) |
18
  | 8B | NuExtract-2.0-8B | [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) | MIT | 🤗 [NuExtract-2.0-8B](https://huggingface.co/numind/NuExtract-2.0-8B) |
19
 
20
  ❗️Note: `NuExtract-2.0-2B` is based on Qwen2-VL rather than Qwen2.5-VL because the smallest Qwen2.5-VL model (3B) has a more restrictive, non-commercial license. We therefore include `NuExtract-2.0-2B` as a small model option that can be used commercially.
 
2
  library_name: transformers
3
  license: mit
4
  base_model:
5
+ - Qwen/Qwen2.5-VL-8B-Instruct
6
  pipeline_tag: image-text-to-text
7
  ---
8
 
9
+ <p align="center">
10
+ <img src="https://cdn.prod.website-files.com/638364a4e52e440048a9529c/64188f405afcf42d0b85b926_logo_numind_final.png" width="200"/>
11
+ <p>
12
+ <p align="center">
13
+ 🖥️ <a href="https://nuextract.ai/">API / Platform</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://numind.ai/blog">Blog</a>&nbsp&nbsp | &nbsp&nbsp🗣️ <a href="https://discord.gg/3tsEtJNCDe">Discord</a>
14
+ </p>
15
+
16
  # NuExtract 2.0 8B by NuMind 📈📈📈
17
 
18
  NuExtract 2.0 is a family of models trained specifically for structured information extraction tasks. It supports both multimodal inputs and is multilingual.
 
21
  | Model Size | Model Name | Base Model | License | Huggingface Link |
22
  |------------|------------|------------|---------|------------------|
23
  | 2B | NuExtract-2.0-2B | [Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) | MIT | 🤗 [NuExtract-2.0-2B](https://huggingface.co/numind/NuExtract-2.0-2B) |
24
+ | 4B | NuExtract-2.0-4B | [Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) | Qwen Research License | 🤗 [NuExtract-2.0-4B](https://huggingface.co/numind/NuExtract-2.0-4B) |
25
  | 8B | NuExtract-2.0-8B | [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) | MIT | 🤗 [NuExtract-2.0-8B](https://huggingface.co/numind/NuExtract-2.0-8B) |
26
 
27
  ❗️Note: `NuExtract-2.0-2B` is based on Qwen2-VL rather than Qwen2.5-VL because the smallest Qwen2.5-VL model (3B) has a more restrictive, non-commercial license. We therefore include `NuExtract-2.0-2B` as a small model option that can be used commercially.