Загрузка видео...
Не удалось загрузить видео
As earlier expected, its been such an intense match, Bugembegembe Falcons 4-0(12) Naluvule Eagles 1-01(4) Sharkul capt of BF is the top scores with 2 goals. Its getting better 🥰 The GAA Please retweet 😇 An updated table standings comes up shortly.#GAA
163,930 просмотров • 3 лет назад •via X (Twitter)
Комментарии: 9
@officialgaa @Global_GAA @LoafPod @KildareFan2023 @AllIrishSport @IrishRepCoE @GlobalIrish @playhurling @AbdullaAlJumali @PaulMurphykk @gaagoofficial The young man in the white here is very very good. He's a natural.
@officialgaa @Global_GAA @LoafPod @KildareFan2023 @AllIrishSport @IrishRepCoE @GlobalIrish @playhurling @AbdullaAlJumali @PaulMurphykk @gaagoofficial He scored the only goal for his side today 🥰
@officialgaa @Global_GAA @LoafPod @KildareFan2023 @AllIrishSport @IrishRepCoE @GlobalIrish @playhurling @AbdullaAlJumali @PaulMurphykk @gaagoofficial There won't be a cow milked in Naluvule in the morning
@officialgaa @Global_GAA @LoafPod @KildareFan2023 @AllIrishSport @IrishRepCoE @GlobalIrish @playhurling @AbdullaAlJumali @PaulMurphykk @gaagoofficial Brilliant fair play to the Ugandans the only nation brave enough to play our games 👏👏🇮🇪
@officialgaa @Global_GAA @LoafPod @KildareFan2023 @AllIrishSport @IrishRepCoE @GlobalIrish @playhurling @AbdullaAlJumali @PaulMurphykk @gaagoofficial @officialgaa Surely a few sets of bibs could be rustled up for these hurlers? Great to see these kids enjoying the game & great to see our games spreading around the world!
@officialgaa @Global_GAA @LoafPod @KildareFan2023 @AllIrishSport @IrishRepCoE @GlobalIrish @playhurling @AbdullaAlJumali @PaulMurphykk @gaagoofficial Super hurling lads fair play to you all
@officialgaa @Global_GAA @LoafPod @KildareFan2023 @AllIrishSport @IrishRepCoE @GlobalIrish @playhurling @AbdullaAlJumali @PaulMurphykk @gaagoofficial I'm not a GAA fan but it's great that the games are spreading around the world
@officialgaa @Global_GAA @LoafPod @KildareFan2023 @AllIrishSport @IrishRepCoE @GlobalIrish @playhurling @AbdullaAlJumali @PaulMurphykk @gaagoofficial The big no 4 could do a job for our junior bs
@officialgaa @Global_GAA @LoafPod @KildareFan2023 @AllIrishSport @IrishRepCoE @GlobalIrish @playhurling @AbdullaAlJumali @PaulMurphykk @gaagoofficial Brilliant Bugemgebenge Falcons! Well done. Keep hurling.
![Self Attention by hand ✍️ ~ 9 steps walkthrough below Self-attention is what enables LLMs to understand context. How does it work? So I drew and calculated one entirely by hand. Goal: turn four 6D features into four 3D attention weighted features, filling in every cell yourself. = 1. Given = Four feature vectors, six dimensions each, one per position. = 2. Query, key, value = Let us multiply the features by WQ, WK and WV. Queries, keys and values all come out of the same four features, and that is what the word "self" is doing in self-attention. = 3. Prepare for MatMul = We copy the queries across the top and the transposed keys down the side. Lining the two up is half the work. = 4. MatMul = Let us multiply K transpose by Q. Every cell is the dot product of one key with one query, which we use as a matching score. That works because the dot product is the numerator of cosine similarity: it is how alike two vectors are, before anyone divides by their lengths. = 5. Scale = We divide by the square root of dk, the dimension of a key vector, here 3. Without it the scores grow with the dimension and a 64-wide head would swamp the softmax. To keep the page doable in pen, the drawing approximates dividing by root 3 with halving. = 6. e to the power = Let us raise e to the power of each score. This is the first half of softmax, and the drawing uses 3 in place of e, which is close enough to do in your head. = 7. Sum = We add up each column: 16, 6, 7 and 12. = 8. Normalize = Let us divide every cell by its column sum. That gives the attention weight matrix in yellow, and each of its four columns is now a probability distribution over the four positions. The decimals are nudged as they are rounded, so every column still sums to exactly 1. = 9. MatMul = We multiply the value vectors by those weights. Each output is a blend of all four values, mixed in the proportion the attention matrix just decided, and it goes to the position-wise feed forward network in the next layer: the FFN box at the bottom of the page. The outputs: Attention weights (A), by column = [.2, .6, 0, .2], [.2, .4, .2, .2], [.4, .2, 0, .4], [.1, .7, .1, .1] Attention weighted features (Z) = [8, 2, 6], [8, 4, 4], [16, 4, 2], [4, 2, 7] The takeaway: attention is a weighted average, and everything before step 9 exists to decide the weights. Compare every position with every other, turn the scores into one distribution per position, then blend. 💾 Save this post!](https://image.24vids.com/tw-2079933315990057242/ext_tw_video_thumb/2079933302048219136/pu/img/q3wr-ymUWG3Ai-ij.jpg)
