Skip to content

v4.42.0: Gemma 2, RTDETR, InstructBLIP, LLAVa Next, New Model Adder

Choose a tag to compare
@LysandreJik LysandreJik released this 27 Jun 15:49
· 151 commits to main since this release

New model additions


The Gemma2 model was proposed in Gemma2: Open Models Based on Gemini Technology and Research by Gemma2 Team, Google.
Gemma2 models are trained on 6T tokens, and released with 2 versions, 2b and 7b.

The abstract from the paper is the following:

This work introduces Gemma2, a new family of open language models demonstrating strong performance across academic benchmarks for language understanding, reasoning, and safety. We release two sizes of models (2 billion and 7 billion parameters), and provide both pretrained and fine-tuned checkpoints. Gemma2 outperforms similarly sized open models on 11 out of 18 text-based tasks, and we present comprehensive evaluations of safety and responsibility aspects of the models, alongside a detailed description of our model development. We believe the responsible release of LLMs is critical for improving the safety of frontier models, and for enabling the next wave of LLM innovations



The RT-DETR model was proposed in DETRs Beat YOLOs on Real-time Object Detection by Wenyu Lv, Yian Zhao, Shangliang Xu, Jinman Wei, Guanzhong Wang, Cheng Cui, Yuning Du, Qingqing Dang, Yi Liu.

RT-DETR is an object detection model that stands for 鈥淩eal-Time DEtection Transformer.鈥 This model is designed to perform object detection tasks with a focus on achieving real-time performance while maintaining high accuracy. Leveraging the transformer architecture, which has gained significant popularity in various fields of deep learning, RT-DETR processes images to identify and locate multiple objects within them.



The InstructBLIP model was proposed in InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning by Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, Steven Hoi. InstructBLIP leverages the BLIP-2 architecture for visual instruction tuning.

InstructBLIP uses the same architecture as BLIP-2 with a tiny but important difference: it also feeds the text prompt (instruction) to the Q-Former.


LlaVa NeXT Video

The LLaVa-NeXT-Video model was proposed in LLaVA-NeXT: A Strong Zero-shot Video Understanding Model by Yuanhan Zhang, Bo Li, Haotian Liu, Yong Jae Lee, Liangke Gui, Di Fu, Jiashi Feng, Ziwei Liu, Chunyuan Li. LLaVa-NeXT-Video improves upon LLaVa-NeXT by fine-tuning on a mix if video and image dataset thus increasing the model鈥檚 performance on videos.

LLaVA-NeXT surprisingly has strong performance in understanding video content in zero-shot fashion with the AnyRes technique that it uses. The AnyRes technique naturally represents a high-resolution image into multiple images. This technique is naturally generalizable to represent videos because videos can be considered as a set of frames (similar to a set of images in LLaVa-NeXT). The current version of LLaVA-NeXT makes use of AnyRes and trains with supervised fine-tuning (SFT) on top of LLaVA-Next on video data to achieves better video understanding capabilities.The model is a current SOTA among open-source models on VideoMME bench.

New model adder

A very significant change makes its way within the transformers codebase, introducing a new way to add models to transformers. We recommend reading the description of the PR below, but here is the gist of it:

The diff_converter tool is here to replace our old Copied from statements, while keeping our core transformers philosophy:

  • single model single file
  • explicit code
  • standardization of modeling code
  • readable and educative code
  • simple code
  • least amount of modularity

This additionally unlocks the ability to very quickly see the differences between new architectures that get developed. While many architectures are similar, the "single model, single file" policy can obfuscate the changes. With this diff converter, we want to make the changes between architectures very explicit.

Tool-use and RAG model support

We've made major updates to our support for tool-use and RAG models. We can now automatically generate JSON schema descriptions for Python functions which are suitable for passing to tool models, and we've defined a standard API for tool models which should allow the same tool inputs to be used with many different models. Models will need updates to their chat templates to support the new API, and we're targeting the Nous-Hermes, Command-R and Mistral/Mixtral model families for support in the very near future. Please see the updated chat template docs for more information.

If you are the owner of a model that supports tool use, but you're not sure how to update its chat template to support the new API, feel free to reach out to us for assistance with the update, for example on the Hugging Face Discord server. Ping Matt and yell key phrases like "chat templates" and "Jinja" and your issue will probably get resolved.

GGUF support

We further the support of GGUF files to offer fine-tuning within the python/HF ecosystem, before converting them back to the GGUF/GGML/llama.cpp libraries.

Trainer improvements

A new optimizer is added in the Trainer.

Quantization improvements

Several improvements are done related to quantization: a new cache (the quantized KV cache) is added, offering the ability to convert the cache of generative models, further reducing the memory requirements.

Additionally, the documentation related to quantization is entirely redone with the aim of helping users choose which is the best quantization method.


New instance segmentation examples are added by @qubvel

Notable improvements

As a notable improvement to the HF vision models that leverage backbones, we enable leveraging HF pretrained model weights as backbones, with the following API:

from transformers import MaskFormerConfig, MaskFormerForInstanceSegmentation

config = MaskFormerConfig(backbone="microsoft/resnet-50", use_pretrained_backbone=True)
model = MaskFormerForInstanceSegmentation(config)

Additionally, we thank @Cyrilvallez for diving into our generate method and greatly reducing the memory requirements.

  • Reduce by 2 the memory requirement in generate() 馃敟馃敟馃敟 by @Cyrilvallez in #30536

Breaking changes

Remove ConversationalPipeline and Conversation object

Both the ConversationalPipeline and the Conversation object have been deprecated for a while, and are due for removal in 4.42, which is the upcoming version.

The TextGenerationPipeline is recommended for this use-case, and now accepts inputs in the form of the OpenAI API.

Remove an accidental duplicate softmax application in FLAVA's attention

Removes duplicate softmax application in FLAVA attention. Likely to have a small change on the outputs but flagging with 馃毃 as it will change a bit.

Idefics2's ignore_index attribute of the loss is updated to -100

out_indices from timm being updated

Recent updates to timm changed the type of the attribute model.feature_info.out_indices. Previously, out_indices would reflect the input type of out_indices on the create_model call i.e. either tuple or list. Now, this value is always a tuple.

As list are more useful and consistent for us -- we cannot save tuples in configs, they must be converted to lists first -- we instead choose to cast out_indices to always be a list.

This has the possibility of being a slight breaking change if users are creating models and relying on out_indices on being a tuple. As this property only happens when a new model is created, and not if it's saved and reloaded (because of the config), then I think this has a low chance of having much of an impact.

datasets referenced in the quantization config get updated to remove references to datasets with restrictive licenses.

Bugfixes and improvements

Significant community contributions

The following contributors have made significant changes to the library over the last release: