timm tiny test models
Collection
A collection of very small (~300-500k parameter) models at 160x160 resolution, for testing purposes. Trained on ImageNet-1k.
•
13 items
•
Updated
•
5
Piyush Maharana
catastropiyush
AI & ML interests
LLMs for scientific data extraction, Solid State Hydrogen Storage,Machine Learning
Recent Activity
upvoted
a
collection
3 days ago
timm tiny test models
liked
a Space
7 days ago
HuggingFaceH4/blogpost-scaling-test-time-compute
liked
a Space
13 days ago
data-is-better-together/fineweb-c-dashboard
Organizations
catastropiyush's activity
upvoted
a
collection
3 days ago
liked
a
Space
7 days ago
liked
a
Space
13 days ago
reacted to
Kseniase's
post with 🔥
13 days ago
Post
2684
TL;DR: The Story of Attention's Development by
@karpathy
Origin: First proposed in 2014 by @Dzmitry Bahdanau, @KyunghyunCho , and Yoshua Bengio in Neural Machine Translation by Jointly Learning to Align and Translate (1409.0473) . Inspired by cognitive processes and later renamed from "RNNSearch."
Key Idea: A data-dependent weighted average for pooling and communication, enabling flexible and powerful neural network connections.
Breakthrough: Bahdanau's "soft search" mechanism (softmax + weighted averaging) solved encoder-decoder bottlenecks in machine translation.
Transformer Revolution: Attention Is All You Need (1706.03762) (2017) by @ashishvaswanigoogle et al. simplified architectures by stacking attention layers, introducing multi-headed attention and positional encodings.
Legacy: Attention replaced RNNs, driving modern AI systems like ChatGPT. It emerged independently but was influenced by contemporaneous work like Alex Graves’s Neural Turing Machines (1410.5401) and Jason Weston’s Memory Networks (1410.3916) .
Attention to history: Jürgen Schmidhuber claims his 1992 Fast Weight Programmers anticipated modern attention mechanisms. While conceptually similar, the term “attention” was absent, and there’s no evidence it influenced Bahdanau, Cho, and Bengio’s 2014 work. Paying attention (!) to history might have brought us to genAI earlier – but credit for the breakthrough still goes to Montreal.
Referenced Papers:
Attention Origin: Neural Machine Translation by Jointly Learning to Align and Translate (1409.0473)
Transformers: Attention Is All You Need (1706.03762)
Alex Graves' Work: Neural Turing Machines (1410.5401), Generating Sequences With Recurrent Neural Networks (1308.0850)
Jason Weston @spermwhale 's Memory Networks (1410.3916)
Sequence to Sequence Learning with Neural Networks (1409.3215) by Ilya Sutskever ( @ilyasut ), Oriol Vinyals, Quoc V. Le
Who else deserves recognition in this groundbreaking narrative of innovation? Let’s ensure every contributor gets the credit they deserve. Leave a comment below 👇🏻🤗
Origin: First proposed in 2014 by @Dzmitry Bahdanau, @KyunghyunCho , and Yoshua Bengio in Neural Machine Translation by Jointly Learning to Align and Translate (1409.0473) . Inspired by cognitive processes and later renamed from "RNNSearch."
Key Idea: A data-dependent weighted average for pooling and communication, enabling flexible and powerful neural network connections.
Breakthrough: Bahdanau's "soft search" mechanism (softmax + weighted averaging) solved encoder-decoder bottlenecks in machine translation.
Transformer Revolution: Attention Is All You Need (1706.03762) (2017) by @ashishvaswanigoogle et al. simplified architectures by stacking attention layers, introducing multi-headed attention and positional encodings.
Legacy: Attention replaced RNNs, driving modern AI systems like ChatGPT. It emerged independently but was influenced by contemporaneous work like Alex Graves’s Neural Turing Machines (1410.5401) and Jason Weston’s Memory Networks (1410.3916) .
Attention to history: Jürgen Schmidhuber claims his 1992 Fast Weight Programmers anticipated modern attention mechanisms. While conceptually similar, the term “attention” was absent, and there’s no evidence it influenced Bahdanau, Cho, and Bengio’s 2014 work. Paying attention (!) to history might have brought us to genAI earlier – but credit for the breakthrough still goes to Montreal.
Referenced Papers:
Attention Origin: Neural Machine Translation by Jointly Learning to Align and Translate (1409.0473)
Transformers: Attention Is All You Need (1706.03762)
Alex Graves' Work: Neural Turing Machines (1410.5401), Generating Sequences With Recurrent Neural Networks (1308.0850)
Jason Weston @spermwhale 's Memory Networks (1410.3916)
Sequence to Sequence Learning with Neural Networks (1409.3215) by Ilya Sutskever ( @ilyasut ), Oriol Vinyals, Quoc V. Le
Who else deserves recognition in this groundbreaking narrative of innovation? Let’s ensure every contributor gets the credit they deserve. Leave a comment below 👇🏻🤗
- 5 replies
upvoted
a
collection
19 days ago
liked
2
models
20 days ago
upvoted
a
collection
20 days ago
liked
a
dataset
23 days ago
authored
a
paper
28 days ago
reacted to
merve's
post with 🔥
29 days ago
Post
3872
Small yet mighty! 💫
We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient 🤠
We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39
Learn more from our blog here: huggingface.co/blog/smolvlm
This release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO 💝
Try the demo: HuggingFaceTB/SmolVLM
Fine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Also TRL integration for DPO 💗
We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient 🤠
We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39
Learn more from our blog here: huggingface.co/blog/smolvlm
This release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO 💝
Try the demo: HuggingFaceTB/SmolVLM
Fine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Also TRL integration for DPO 💗
liked
a
dataset
about 1 month ago
updated
a
model
about 2 months ago
liked
a
dataset
3 months ago
liked
a
model
3 months ago
updated
a
model
3 months ago
liked
a
model
4 months ago
upvoted
2
articles
4 months ago
Article
Open LLM Leaderboard: DROP deep dive
•
5
Article
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
•
102
liked
a
Space
4 months ago