Update README.md

README.md

@@ -5,9 +5,9 @@ tags: []
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
-
+SmolVLM is a compact open multimodal model that accepts arbitrary sequences of image and text inputs to produce text outputs. Designed for efficiency, SmolVLM can answer questions about images, describe visual content, create stories grounded on multiple images, or function as a pure language model without visual inputs. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks.
 
+We release the checkpoints under the Apache 2.0 license.
 
 ## Model Details
 
@@ -17,13 +17,10 @@ tags: []
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Developed by:** Hugging Face 🤗
+- **Model type:** Multi-modal model (image+text)
+- **Language(s) (NLP):** English
+- **License:** Apache 2.0
 
 ### Model Sources [optional]
 
@@ -31,55 +28,124 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 - **Repository:** [More Information Needed]
 - **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Demo [optional]:** https://huggingface.co/spaces/HuggingFaceTB/SmolVLM
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+SmolVLM can be used for inference on multimodal (image + text) tasks where the input comprises text queries along with one or more images. Text and images can be interleaved arbitrarily, enabling tasks like image captioning, visual question answering, and storytelling based on visual content. The model does not support image generation.
 
-### Direct Use
+To fine-tune SmolVLM on a specific task, you can follow the fine-tuning tutorial.
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+### Technical Summary
 
-[More Information Needed]
+SmolVLM leverages the lightweight SmolLM2 language model to provide a compact yet powerful multimodal experience. It introduces several changes compared to previous models:
 
-### Downstream Use [optional]
+- Image compression: We introduce a more radical image compression compared to Idefics3 to enable the model to infer faster and use less RAM.
+- Visual Token Encoding: It uses 81 visual tokens to encode image patches of size 384*384. Larger images are divided into patches, each encoded separately, enhancing efficiency without compromising performance.
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+More details about the training and architecture are available in our technical report.
 
-[More Information Needed]
 
-### Out-of-Scope Use
+### How to get started
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+```python
+import torch
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForVision2Seq
+from transformers.image_utils import load_image
 
-[More Information Needed]
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 
-## Bias, Risks, and Limitations
+# Load images
+image1 = load_image("https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg")
+image2 = load_image("https://huggingface.co/spaces/merve/chameleon-7b/resolve/main/bee.jpg")
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+# Initialize processor and model
+processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-Instruct")
+model = AutoModelForVision2Seq.from_pretrained(
+    "HuggingFaceTB/SmolVLM-Instruct", torch_dtype=torch.bfloat16
+).to(DEVICE)
 
-[More Information Needed]
+# Create input messages
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image"},
+            {"type": "text", "text": "What do we see in this image?"}
+        ]
+    },
+    {
+        "role": "assistant",
+        "content": [
+            {"type": "text", "text": "This image shows a city skyline with prominent landmarks."}
+        ]
+    },
+    {
+        "role": "user",
+        "content": [
+            {"type": "image"},
+            {"type": "text", "text": "And how about this image?"}
+        ]
+    }
+]
 
-### Recommendations
+# Prepare inputs
+prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
+inputs = processor(text=prompt, images=[image1, image2], return_tensors="pt")
+inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+# Generate outputs
+generated_ids = model.generate(**inputs, max_new_tokens=500)
+generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+print(generated_texts[0])
+```
 
-## How to Get Started with the Model
 
-Use the code below to get started with the model.
+### Model optimizations
+
+**Precision**: For better performance, load and run the model in half-precision (`torch.float16` or `torch.bfloat16`) if your hardware supports it.
+
+```python
+model = AutoModelForVision2Seq.from_pretrained(
+    "HuggingFaceTB/SmolVLM-Instruct",
+    torch_dtype=torch.bfloat16
+).to(DEVICE)
+```
+
+**Vision Encoder Efficiency**: Adjust the image resolution by setting size={"longest_edge": N*384} when initializing the processor, where N is your desired value. The default N=4 works well, but for documents, N=5 might be beneficial. Decreasing N can save GPU memory for lower-resolution images. This is also useful if you want to fine-tune on videos.
 
-[More Information Needed]
+
+## Misuse and Out-of-scope Use
+
+SmolVLM is not intended for high-stakes scenarios or critical decision-making processes that affect an individual's well-being or livelihood. The model may produce content that appears factual but may not be accurate. Misuse includes, but is not limited to:
+
+- Prohibited Uses:
+  - Evaluating or scoring individuals (e.g., in employment, education, credit)
+  - Critical automated decision-making
+  - Generating unreliable factual content
+- Malicious Activities:
+  - Spam generation
+  - Disinformation campaigns
+  - Harassment or abuse
+  - Unauthorized surveillance
+
+### License
+
+SmolVLM is built upon the following pre-trained models:
+
+https://huggingface.co/google/siglip-so400m-patch14-384
+https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct
+
+We release the SmolVLM checkpoints under the Apache 2.0 license.
 
 ## Training Details
 
 ### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+The training data 
 
-[More Information Needed]
 
 ### Training Procedure