Model card suggestions

README.md

@@ -5,45 +5,42 @@ datasets:
 - HuggingFaceM4/the_cauldron
 - HuggingFaceM4/Docmatix
 pipeline_tag: image-text-to-text
+language:
+- en
 ---
 
-# Model Card for Model ID
+# SmolVLM Instruct
 
 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.
 
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+## Model Summary
 
 - **Developed by:** Hugging Face 🤗
 - **Model type:** Multi-modal model (image+text)
 - **Language(s) (NLP):** English
 - **License:** Apache 2.0
+- **Architecture:** Based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) (see more details below)
 
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
+## Resources
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
 - **Demo:** [SmolVLM Demo](https://huggingface.co/spaces/HuggingFaceTB/SmolVLM)
+- **Blog:** [More Information Needed]
+- **Technical Report:** [More Information Needed]
+- **Repository:** [More Information Needed]
 
 ## Uses
 
 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.
 
 To fine-tune SmolVLM on a specific task, you can follow the fine-tuning tutorial.
+<!-- todo: add link to fine-tuning tutorial -->
 
 ### Technical Summary
 
-SmolVLM leverages the lightweight SmolLM2 language model to provide a compact yet powerful multimodal experience. It introduces several changes compared to previous models:
+SmolVLM leverages the lightweight SmolLM2 language model to provide a compact yet powerful multimodal experience. It introduces several changes compared to previous Idefics models:
 
 - **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.
+- **Visual Token Encoding:** SmolVLM 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.
 
 More details about the training and architecture are available in our technical report.
 
@@ -67,7 +64,8 @@ image2 = load_image("https://huggingface.co/spaces/merve/chameleon-7b/resolve/ma
 # Initialize processor and model
 processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-Instruct")
 model = AutoModelForVision2Seq.from_pretrained(
-    "HuggingFaceTB/SmolVLM-Instruct", torch_dtype=torch.bfloat16
+    "HuggingFaceTB/SmolVLM-Instruct",
+    torch_dtype=torch.bfloat16,
 ).to(DEVICE)
 
 # Create input messages
@@ -97,11 +95,14 @@ messages = [
 # 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()}
+inputs = inputs.to(DEVICE)
 
 # Generate outputs
 generated_ids = model.generate(**inputs, max_new_tokens=500)
-generated_texts = processor.batch_decode(generated_ids, skip_special_tokens=True)
+generated_texts = processor.batch_decode(
+    generated_ids,
+    skip_special_tokens=True,
+)
 
 print(generated_texts[0])
 ```
@@ -130,11 +131,12 @@ import torch
 quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 model = AutoModelForVision2Seq.from_pretrained(
     "HuggingFaceTB/SmolVLM-Instruct",
-    quantization_config=quantization_config
+    quantization_config=quantization_config,
 )
 ```
 
-**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.
+**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, which results in input images of
+size 1536×1536. For documents, `N=5` might be beneficial. Decreasing N can save GPU memory and is appropriate for lower-resolution images. This is also useful if you want to fine-tune on videos.
 
 
 ## Misuse and Out-of-scope Use