--- license: apache-2.0 language: - en datasets: - HuggingFaceM4/RAVEN tags: - code --- **Try out the [demo](https://huggingface.co/spaces/HuggingFaceM4/ai_raven)!** # Model Description This model was trained to solve Raven's Progressive Matrices. It is based on an early checkpoint of our upcoming vision-language foundation model. We use the [RAVEN](https://huggingface.co/datasets/HuggingFaceM4/RAVEN) dataset of procedurally generated Raven puzzles to train the system. On the validation set, the model would reach 91% accuracy. # Code snippet The model has been specifically fine-tuned for solving Raven puzzles and we cannot guarantee that it will behave accurately outside of this use-case with no proper adaptation. The code snippet how to do batch inference with the model. A lot of the input preparation will be encapsulated once we integrate the model into HF Transformers. ```python import torch import requests from io import BytesIO from PIL import Image from transformers import AutoModelForCausalLM, AutoProcessor from transformers.image_utils import to_numpy_array, PILImageResampling, ChannelDimension from transformers.image_transforms import resize, to_channel_dimension_format DEVICE = torch.device("cuda") PROCESSOR = AutoProcessor.from_pretrained( "HuggingFaceM4/tr_272_bis_opt_step_15000_merge", token=API_TOKEN, ) MODEL = AutoModelForCausalLM.from_pretrained( "HuggingFaceM4/tr_272_bis_opt_step_15000_merge", token=API_TOKEN, trust_remote_code=True, torch_dtype=torch.bfloat16, ).to(DEVICE) image_seq_len = MODEL.config.perceiver_config.resampler_n_latents BOS_TOKEN = PROCESSOR.tokenizer.bos_token BAD_WORDS_IDS = PROCESSOR.tokenizer(["", ""], add_special_tokens=False).input_ids def convert_to_rgb(image): # `image.convert("RGB")` would only work for .jpg images, as it creates a wrong background # for transparent images. The call to `alpha_composite` handles this case if image.mode == "RGB": return image image_rgba = image.convert("RGBA") background = Image.new("RGBA", image_rgba.size, (255, 255, 255)) alpha_composite = Image.alpha_composite(background, image_rgba) alpha_composite = alpha_composite.convert("RGB") return alpha_composite # The processor is the same as the Idefics processor except for the BILINEAR interpolation, # so this is a hack in order to redefine ONLY the transform method def custom_transform(x): x = convert_to_rgb(x) x = to_numpy_array(x) height, width = x.shape[:2] aspect_ratio = width / height if width >= height and width > 980: width = 980 height = int(width / aspect_ratio) elif height > width and height > 980: height = 980 width = int(height * aspect_ratio) width = max(width, 378) height = max(height, 378) x = resize(x, (height, width), resample=PILImageResampling.BILINEAR) x = PROCESSOR.image_processor.rescale(x, scale=1 / 255) x = PROCESSOR.image_processor.normalize( x, mean=PROCESSOR.image_processor.image_mean, std=PROCESSOR.image_processor.image_std ) x = to_channel_dimension_format(x, ChannelDimension.FIRST) x = torch.tensor(x) return x # Create text token inputs image_seq = '' * image_seq_len inputs = PROCESSOR.tokenizer( [ f"{BOS_TOKEN}User:{image_seq}Which figure should complete the logical sequence?\nAssistant:", f"{BOS_TOKEN}User:{image_seq}Which figure should complete the logical sequence?\nAssistant:", ], return_tensors="pt", add_special_tokens=False, padding=True, ) # Create pixel inputs raw_images = [ [your_raven_puzzle_as_a_pil_image1], [your_raven_puzzle_as_a_pil_image2], ] output_images = [ [PROCESSOR.image_processor(img, transform=custom_transform) for img in img_list] for img_list in raw_images ] total_batch_size = len(output_images) max_num_images = max([len(img_l) for img_l in output_images]) max_height = max([i.size(2) for img_l in output_images for i in img_l]) max_width = max([i.size(3) for img_l in output_images for i in img_l]) padded_image_tensor = torch.zeros(total_batch_size, max_num_images, 3, max_height, max_width) padded_pixel_attention_masks = torch.zeros( total_batch_size, max_num_images, max_height, max_width, dtype=torch.bool ) for batch_idx, img_l in enumerate(output_images): for img_idx, img in enumerate(img_l): im_height, im_width = img.size()[2:] padded_image_tensor[batch_idx, img_idx, :, :im_height, :im_width] = img padded_pixel_attention_masks[batch_idx, img_idx, :im_height, :im_width] = True inputs["pixel_values"] = padded_image_tensor inputs["pixel_attention_mask"] = padded_pixel_attention_masks inputs = {k: v.to(DEVICE) for k, v in inputs.items()} generated_ids = MODEL.generate(**inputs, bad_words_ids=BAD_WORDS_IDS, max_new_tokens=10) generated_texts = PROCESSOR.batch_decode(generated_ids, skip_special_tokens=True) print(generated_texts) ``` # Model Details - **Developed by:** Hugging Face - **Model type:** Multi-modal model - **Language(s) (NLP):** en - **License:** see [License section](#license) - **Parent Models:** [SigLIP](https://github.com/huggingface/transformers/pull/26522) and [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) - **Resources for more information:** - RAVEN dataset: [Dataset card](https://huggingface.co/datasets/HuggingFaceM4/RAVEN) # License The model is built on top of two pre-trained models: [SigLIP](https://github.com/huggingface/transformers/pull/26522) and [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1), which are delivered under an Apache-2.0 license. As such, users should comply with the licenses of these models. The two pre-trained models are connected to each other with newly initialized parameters that we train. These are not based on any of the two base frozen models forming the composite model. We release the additional weights we trained under an Apache-2.0 license.