Sourced from transformers's releases.
Release v5.5.0
New Model additions
Gemma4
Gemma 4 is a multimodal model with pretrained and instruction-tuned variants, available in 1B, 13B, and 27B parameters. The architecture is mostly the same as the previous Gemma versions. The key differences are a vision processor that can output images of fixed token budget and a spatial 2D RoPE to encode vision-specific information across height and width axis.
You can find all the original Gemma 4 checkpoints under the Gemma 4 release.
The key difference from previous Gemma releases is the new design to process images of different sizes using a fixed-budget number of tokens. Unlike many models that squash every image into a fixed square (like 224×224), Gemma 4 keeps the image's natural aspect ratio while making it the right size. There a a couple constraints to follow:
- The total number of pixels must fit within a patch budget
- Both height and width must be divisible by 48 (= patch size 16 × pooling kernel 3)
[!IMPORTANT] Gemma 4 does not apply the standard ImageNet mean/std normalization that many other vision models use. The model's own patch embedding layer handles the final scaling internally (shifting values to the [-1, 1] range).
The number of "soft tokens" (aka vision tokens) an image processor can produce is configurable. The supported options are outlined below and the default is 280 soft tokens per image.
Soft Tokens Patches (before pooling) Approx. Image Area 70 630 ~161K pixels 140 1,260 ~323K pixels 280 2,520 ~645K pixels 560 5,040 ~1.3M pixels 1,120 10,080 ~2.6M pixels To encode positional information for each patch in the image, Gemma 4 uses a learned 2D position embedding table. The position table stores up to 10,240 positions per axis, which allows the model to handle very large images. Each position is a learned vector of the same dimensions as the patch embedding. The 2D RoPE which Gemma 4 uses independently rotate half the attention head dimensions for the x-axis and the other half for the y-axis. This allows the model to understand spatial relationships like "above," "below," "left of," and "right of."
NomicBERT
NomicBERT is a BERT-inspired encoder model that applies Rotary Position Embeddings (RoPE) to create reproducible long context text embeddings. It is the first fully reproducible, open-source text embedding model with 8192 context length that outperforms both OpenAI Ada-002 and OpenAI text-embedding-3-small on short-context MTEB and long context LoCo benchmarks. The model generates dense vector embeddings for various tasks including search, clustering, and classification using specific instruction prefixes.
Links: Documentation | Paper
MusicFlamingo
Music Flamingo is a fully open large audio–language model designed for robust understanding and reasoning over music. It builds upon the Audio Flamingo 3 architecture by including Rotary Time Embeddings (RoTE), which injects temporal position information to enable the model to handle audio sequences up to 20 minutes. The model features a unified audio encoder across speech, sound, and music with special sound boundary tokens for improved audio sequence modeling.
Links: Documentation | Paper
- Add Music Flamingo (#43538) by
@lashahubin #43538
... (truncated)
c1c3424
update20bff68
update release workflow8956441
v5.5.05135e5e
casually dropping the most capable open weights on the planet (#45192)a594e09
Internalise the NomicBERT model (#43067)4932e97
Fix resized LM head weights being overwritten by post_init (#45079)57e8413
[Qwen3.5 MoE] Add _tp_plan to ForConditionalGeneration (#45124)b10552e
Fix TypeError: 'NoneType' object is not iterable in
GenerationMixin.generate ...423f2a3
fix(models): Fix dtype mismatch in SwitchTransformers and
TimmWrapperModel (#...ade7a05
Generalize gemma vision mask to videos (#45185)