Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,17 @@
|
|
1 |
---
|
2 |
-
name: BSAtlas Model
|
3 |
-
tags:
|
4 |
-
- image-to-text
|
5 |
-
- transformers
|
6 |
-
- unsloth
|
7 |
-
- chat-bot
|
8 |
-
- mllm
|
9 |
license: apache-2.0
|
10 |
language:
|
11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
description: |
|
13 |
The BSAtlas Model is a multimodal large language model designed for advanced text generation and chatbot applications. Developed by BS|MedX, it supports both text and image inputs, or either, enabling rich contextual understanding and versatile responses.
|
14 |
features:
|
@@ -48,5 +51,4 @@ image = Image.open("path/to/image.jpg")
|
|
48 |
image_features = model.process_image(image) # Replace with your image processing logic
|
49 |
inputs = tokenizer("Analyze this image:", return_tensors="pt")
|
50 |
outputs = model.generate(**inputs, image_features=image_features)
|
51 |
-
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
52 |
-
|
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
language:
|
4 |
+
- en
|
5 |
+
- ar
|
6 |
+
- fr
|
7 |
+
- de
|
8 |
+
- hi
|
9 |
+
- he
|
10 |
+
- ru
|
11 |
+
new_version: BSAtlas/BS_MedX_MedChat
|
12 |
+
pipeline_tag: image-to-text
|
13 |
+
---
|
14 |
+
---
|
15 |
description: |
|
16 |
The BSAtlas Model is a multimodal large language model designed for advanced text generation and chatbot applications. Developed by BS|MedX, it supports both text and image inputs, or either, enabling rich contextual understanding and versatile responses.
|
17 |
features:
|
|
|
51 |
image_features = model.process_image(image) # Replace with your image processing logic
|
52 |
inputs = tokenizer("Analyze this image:", return_tensors="pt")
|
53 |
outputs = model.generate(**inputs, image_features=image_features)
|
54 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|