Hugging Face's logo
dame rajee's picture
34 95 227

dame rajee

damerajee
lunarflu's profile picture Theartplug's profile picture Dragunflie-420's profile picture
·

AI & ML interests

None yet

Recent Activity

reacted to Kseniase's post with ❤️ about 9 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 👀 about 9 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 👀 about 9 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.
View all activity

Organizations

Blog-explorers's profile picture Samanvay AI's profile picture None yet's profile picture

Posts 2

view post
Post
500
On the 2nd of October a really cool paper was released called "Were RNNs all we need" https://arxiv.org/abs/2410.01201

This paper introduces the MinGRU model, a simplified version of the traditional Gated Recurrent Unit (GRU) designed to enhance efficiency by removing hidden state dependencies from its gates. This allows for parallel training, making it significantly faster than conventional GRUs. Additionally, MinGRU eliminates non-linear activations like tanh, streamlining computations.

So I read the paper and I tried training this model and it seems to be doing quite well , you could check out the pre-trained model on the huggingface spaces

- damerajee/mingru-stories
view post
Post
1930
Just released ViLaH - a compact 3B parameter vision language model! which generates responses in Hindi only hindi for now 😔

BhashaAI/ViLaH
View all Posts

Collections 5