tolgacangoz (Tolga Cangöz)

8 types of RoPE

As we always use Transformers, it's helpful to understand RoPE—Rotary Position Embedding. Since token order matters, RoPE encodes it by rotating token embeddings based on their position, so the model knows how to interpret which token comes first, second, and so on.

Here are 8 types of RoPE that can be implemented in different cases:

1. Original RoPE -> RoFormer: Enhanced Transformer with Rotary Position Embedding (2104.09864)
Encodes token positions by rotating token embeddings in the complex plane via a position-based rotation matrix, thereby providing the self-attention mechanism with relative positional info.

2. LongRoPE -> LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens (2402.13753)
Extends the context window of pre-trained LLMs to 2048k tokens, leveraging non-uniformities in positional interpolation with an efficient search.

3. LongRoPE2 -> LongRoPE2: Near-Lossless LLM Context Window Scaling (2502.20082)
Extends the effective context window of pre-trained LLMs to the target! length, rescaling RoPE guided by “needle-driven” perplexity.

4. Multimodal RoPE (MRoPE) -> Qwen2.5-VL Technical Report (2502.13923)
Decomposes positional embedding into 3 components: temporal, height and width, so that positional features are aligned across modalities: text, images and videos.

5. Directional RoPE (DRoPE) -> DRoPE: Directional Rotary Position Embedding for Efficient Agent Interaction Modeling (2503.15029)
Adds an identity scalar, improving how angles are handled without extra complexity. It helps balance accuracy, speed, and memory usage.

6. VideoRoPE -> VideoRoPE: What Makes for Good Video Rotary Position Embedding? (2502.05173)
Adapts RoPE for video, featuring 3D structure, low-frequency temporal allocation, diagonal layout, and adjustable spacing.

7. VRoPE -> VRoPE: Rotary Position Embedding for Video Large Language Models (2502.11664)
An another RoPE for video, which restructures positional indices and balances encoding for uniform spatial focus.

8. XPos (Extrapolatable Position Embedding) -> https://huggingface.co/papers/2212.10
Introduces an exponential decay factor into the rotation matrix, improving stability on long sequences.

1 reply

·

liked a Space about 1 month ago

135

Remade Effects

🦀

Generate videos from images with specific effects

upvoted a collection about 1 month ago

Open-Sora 2.0

Collection

3 items • Updated Mar 12 • 12

New activity in hunyuanvideo-community/HunyuanVideo-I2V-33ch about 1 month ago

https://github.com/huggingface/diffusers/pull/10983#issuecomment-2712782698

2

#1 opened about 1 month ago by

tolgacangoz

New activity in tencent/HunyuanVideo-I2V about 1 month ago

when to release hunyuanvideo-i2v-diffusers?

1

#5 opened about 1 month ago by

Nicola007

reacted to tomaarsen's post with ❤️ about 1 month ago

Post

6660

An assembly of 18 European companies, labs, and universities have banded together to launch 🇪🇺 EuroBERT! It's a state-of-the-art multilingual encoder for 15 European languages, designed to be finetuned for retrieval, classification, etc.

🇪🇺 15 Languages: English, French, German, Spanish, Chinese, Italian, Russian, Polish, Portuguese, Japanese, Vietnamese, Dutch, Arabic, Turkish, Hindi
3️⃣ 3 model sizes: 210M, 610M, and 2.1B parameters - very very useful sizes in my opinion
➡️ Sequence length of 8192 tokens! Nice to see these higher sequence lengths for encoders becoming more common.
⚙️ Architecture based on Llama, but with bi-directional (non-causal) attention to turn it into an encoder. Flash Attention 2 is supported.
🔥 A new Pareto frontier (stronger *and* smaller) for multilingual encoder models
📊 Evaluated against mDeBERTa, mGTE, XLM-RoBERTa for Retrieval, Classification, and Regression (after finetuning for each task separately): EuroBERT punches way above its weight.
📝 Detailed paper with all details, incl. data: FineWeb for English and CulturaX for multilingual data, The Stack v2 and Proof-Pile-2 for code.

Check out the release blogpost here: https://huggingface.co/blog/EuroBERT/release
* EuroBERT/EuroBERT-210m
* EuroBERT/EuroBERT-610m
* EuroBERT/EuroBERT-2.1B

The next step is for researchers to build upon the 3 EuroBERT base models and publish strong retrieval, zero-shot classification, etc. models for all to use. I'm very much looking forward to it!