Update README.md

README.md

@@ -36,20 +36,28 @@ The model is developed to process diverse inputs, including images and text, fac
 
 Cephalo provides a robust framework for multimodal interaction and understanding, including the development of complex generative pipelines to create 2D and 3D renderings of material microstructures as input for additive manufacturing methods.
 
-This version of Cephalo, ```lamm-mit/Cephalo-Llama-3.2-11B-Vision-Instruct-128k```, is based on the ```meta-llama/Llama-3.2-11B-Vision-Instruct``` model. The model was trained on a combination of scientific text-image data extracted from Wikipedia and scientific papers. For further details on the base model, see: https://huggingface.co/HuggingFaceM4/idefics2-8b-chatty. More details about technical aspects of the model, training and example applications to materials science problems are provided in the paper (reference at the bottom).
+This version of Cephalo, ```lamm-mit/Cephalo-Llama-3.2-11B-Vision-Instruct-128k```, is based on the ```meta-llama/Llama-3.2-11B-Vision-Instruct``` model. The model was trained on a combination of scientific text-image data extracted from Wikipedia and scientific papers. 
+
+For further details on the base model, see: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct. More details about technical aspects of the model, training and example applications to materials science problems are provided in the paper (reference at the bottom).
 
 ### Chat Format
 
 The ```lamm-mit/Cephalo-Llama-3.2-11B-Vision-Instruct-128k``` is suiteable for one or more image inputs, wih prompts using the chat format as follows:
 
 ```raw
-[{'role': 'user',
+messages=[{'role': 'user',
   'content': [{'type': 'image'},
    {'type': 'text',
-    'text': 'What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI. \n\nFirst brainstorm, then organize your thoughts, then respond.'}]},
- {'role': 'assistant',
-  'content': [{'type': 'text',
-    'text': 'The image shows a group of ants working together to move a large object. This scene illustrates the concept of swarm intelligence, where individual agents (ants) collectively achieve a complex task through decentralized, self-organized behavior. \n\nIn materials design, this concept can be applied to develop new materials and structures by mimicking the behavior of swarms. For instance, researchers have used swarm intelligence algorithms to optimize the design of composite materials, such as fiber-reinforced polymers, by simulating the behavior of ants or other swarming organisms. These algorithms can help identify the optimal arrangement of fibers to maximize strength and minimize weight.\n\nMulti-agent AI, which involves the coordination of multiple autonomous agents to achieve a common goal, can also be used in materials design. This approach can be applied to simulate the behavior of complex systems, such as biological tissues or nanomaterials, and optimize their properties through machine learning algorithms. By analyzing the behavior of individual agents and their interactions, researchers can develop new materials with improved performance and functionality.\n\nIn summary, the image of ants working together to move a large object serves as a metaphor for the potential of swarm intelligence and multi-agent AI in materials design. By mimicking the behavior of swarms, researchers can develop new materials and structures with improved properties and functionality.'}]}]
+    'text': 'Consider the stress-strain response under compression. What are the three curves shown. Based on an inspection of the plot, do they show good agreement or are they very different?'}]}]
+```
+After application of the chat template:
+
+```python
+input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
+```
+The raw input text is:
+```raw
+<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\n<|image|>Consider the stress-strain response under compression. What are the three curves shown. Based on an inspection of the plot, do they show good agreement or are they very different?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n
 ```
 
 ### Sample inference code
@@ -81,8 +89,8 @@ from PIL import Image
 
 url = "https://huggingface.co/lamm-mit/Cephalo-Llama-3.2-11B-Vision-Instruct-128k/resolve/main/architected_stress_strain.png"
 
-image = Image.open(requests.get(url, stream=True).raw)
-
+image = Image.open(requests.get(url, stream=True ).raw)
+images = [image]
 messages = [
     {"role": "user", "content": [
         {"type": "image"},
@@ -90,7 +98,7 @@ messages = [
     ]}
 ]
 input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
-inputs = processor(image, input_text, return_tensors="pt").to(model.device)
+inputs = processor(images, input_text, return_tensors="pt").to(model.device)
 
 output = model.generate(**inputs, max_new_tokens=512)
 print(processor.decode(output[0]))