Hugging Face's logo
Mariusz Kurman's picture
19 3 20

Mariusz Kurman PRO

mkurman
vivekrp's profile picture Fishtiks's profile picture adeidei's profile picture
·

AI & ML interests

AI Tech Lead | MD

Recent Activity

reacted to Kseniase's post with 👀 about 22 hours ago
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 -> https://huggingface.co/papers/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 -> https://huggingface.co/papers/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 -> https://huggingface.co/papers/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) -> https://huggingface.co/papers/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) -> https://huggingface.co/papers/2503.15029 Adds an identity scalar, improving how angles are handled without extra complexity. It helps balance accuracy, speed, and memory usage. 6. VideoRoPE -> https://huggingface.co/papers/2502.05173 Adapts RoPE for video, featuring 3D structure, low-frequency temporal allocation, diagonal layout, and adjustable spacing. 7. VRoPE -> https://huggingface.co/papers/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.
reacted to Kseniase's post with 🔥 8 days ago
15 types of attention mechanisms Attention mechanisms allow models to dynamically focus on specific parts of their input when performing tasks. In our recent article, we discussed Multi-Head Latent Attention (MLA) in detail and now it's time to summarize other existing types of attention. Here is a list of 15 types of attention mechanisms used in AI models: 1. Soft attention (Deterministic attention) -> https://huggingface.co/papers/1409.0473 Assigns a continuous weight distribution over all parts of the input. It produces a weighted sum of the input using attention weights that sum to 1. 2. Hard attention (Stochastic attention) -> https://huggingface.co/papers/1508.04025 Makes a discrete selection of some part of the input to focus on at each step, rather than attending to everything. 3. Self-attention -> https://huggingface.co/papers/1706.03762 Each element in the sequence "looks" at other elements and "decides" how much to borrow from each of them for its new representation. 4. Cross-Attention (Encoder-Decoder attention) -> https://huggingface.co/papers/2104.08771 The queries come from one sequence and the keys/values come from another sequence. It allows a model to combine information from two different sources. 5. Multi-Head Attention (MHA) -> https://huggingface.co/papers/1706.03762 Multiple attention “heads” are run in parallel.​ The model computes several attention distributions (heads), each with its own set of learned projections of queries, keys, and values. 6. Multi-Head Latent Attention (MLA) -> https://huggingface.co/papers/2405.04434 Extends MHA by incorporating a latent space where attention heads can dynamically learn different latent factors or representations. 7. Memory-Based attention -> https://huggingface.co/papers/1503.08895 Involves an external memory and uses attention to read from and write to this memory. See other types in the comments 👇
reacted to BrigitteTousi's post with ❤️ 13 days ago
LeRobot goes to driving school! 🚗🚗🚗 Hugging Face just announced a new collab with Yaak to bring the largest open-source self-driving dataset to LeRobot! Major kudos to HF's @cadene, as well as @sandhawalia, @Shnissen and the Yaak team! Check out the blog post here: https://huggingface.co/blog/lerobot-goes-to-driving-school
View all activity

Organizations

MedIT Solutions's profile picture BigScience Biomedical Datasets's profile picture SOWA Project's profile picture

mkurman's activity

upvoted a collection 5 months ago
upvoted an article 10 months ago
view article
Article

Space secrets security update

• 50