4rtemi5/tsb_bert_dataset
Viewer
โข
Updated
โข
80.5M
โข
55
Raphael Pisoni
4rtemi5
AI & ML interests
None yet
Recent Activity
updated
a dataset
9 days ago
4rtemi5/tsb_bert_dataset
updated
a dataset
9 days ago
4rtemi5/processed_tsb_bert_dataset
updated
a model
9 days ago
4rtemi5/tsb_bert-base-uncased
Organizations
4rtemi5's activity
updated
2
datasets
9 days ago
updated
a
model
9 days ago
reacted to
clem's
post with โค๏ธ
3 months ago
Post
4165
Open-source AI creates healthy competition in a field where natural tendencies lead to extreme concentration of power. Imagine a world where only one or two companies could build software. This is the biggest risk and ethical challenge of them all IMO. Let's fight this!
- 3 replies
reacted to
singhsidhukuldeep's
post with ๐ฅ
4 months ago
Post
1222
Remember when
@Google
launched MediaPipe in an effort to create efficient on-device pipelines?
They've just unlocked the ability to run 7B+ parameter language models directly in your browser. This is a game-changer for on-device AI!
Yes, they are streaming 8.6 GB model files!
Currently, they have Gemma 2B/7B running, but imagine Dynamic LoRA, multimodal support, quantization, and you never leaving Chrome!
This is a significant technical advancement, especially in Memory Optimization:
- Redesigned the model-loading code to work around WebAssembly's 4 GB memory limit.
- Implemented asynchronous loading of transformer stack layers (28 for Gemma 1.1 7B).
- Reduced peak WebAssembly memory usage to less than 1% of previous requirements.
Cross-Platform Compatibility
- Compiled the C++ codebase to WebAssembly for broad browser support.
- Utilized the WebGPU API for native GPU acceleration in browsers.
Here's why this matters:
1. Privacy: No need to send data to remote servers.
2. Cost-Efficiency: Eliminates server expenses.
3. Offline Capabilities: Use powerful AI without an internet connection.
Blog: https://research.google/blog/unlocking-7b-language-models-in-your-browser-a-deep-dive-with-google-ai-edges-mediapipe/
They've just unlocked the ability to run 7B+ parameter language models directly in your browser. This is a game-changer for on-device AI!
Yes, they are streaming 8.6 GB model files!
Currently, they have Gemma 2B/7B running, but imagine Dynamic LoRA, multimodal support, quantization, and you never leaving Chrome!
This is a significant technical advancement, especially in Memory Optimization:
- Redesigned the model-loading code to work around WebAssembly's 4 GB memory limit.
- Implemented asynchronous loading of transformer stack layers (28 for Gemma 1.1 7B).
- Reduced peak WebAssembly memory usage to less than 1% of previous requirements.
Cross-Platform Compatibility
- Compiled the C++ codebase to WebAssembly for broad browser support.
- Utilized the WebGPU API for native GPU acceleration in browsers.
Here's why this matters:
1. Privacy: No need to send data to remote servers.
2. Cost-Efficiency: Eliminates server expenses.
3. Offline Capabilities: Use powerful AI without an internet connection.
Blog: https://research.google/blog/unlocking-7b-language-models-in-your-browser-a-deep-dive-with-google-ai-edges-mediapipe/
reacted to
anakin87's
post with ๐ฅ
5 months ago
Post
1667
๐ฌ ๐ฎ๐น Phi 3.5 mini ITA: a Small Language Model for Italian
Lately, I've spent some time fine-tuning language models.
Now I am happy to release Phi 3.5 mini ITA: a fine-tuned version of Phi-3.5-mini-instruct to improve performance on the Italian language
๐น Small (3.82 B parameters) but capable model
๐น 128k context length
Chat with it on ๐ค Spaces: anakin87/Phi-3.5-mini-ITA
Model card: anakin87/Phi-3.5-mini-ITA
๐๏ธ Data
Supervised fine-tuning using a good mix of English and Italian data:
- mlabonne/FineTome-100k by @mlabonne
- efederici/capybara-claude-15k-ita by @efederici
๐ Thanks to the authors for the datasets.
๐ฏ Targeted training with Spectrum
I used Spectrum, a relatively new technique for parameter-efficient learning.
The idea is to train only the layers of the model with high Signal-to-Noise Ratio (SNR) and โ๏ธ freeze the rest.
I trained the top 30% of model layers.
๐ Spectrum paper: https://arxiv.org/abs/2406.06623
๐ Vibe check and performance on Italian benchmarks seem encouraging
Lately, I've spent some time fine-tuning language models.
Now I am happy to release Phi 3.5 mini ITA: a fine-tuned version of Phi-3.5-mini-instruct to improve performance on the Italian language
๐น Small (3.82 B parameters) but capable model
๐น 128k context length
Chat with it on ๐ค Spaces: anakin87/Phi-3.5-mini-ITA
Model card: anakin87/Phi-3.5-mini-ITA
๐๏ธ Data
Supervised fine-tuning using a good mix of English and Italian data:
- mlabonne/FineTome-100k by @mlabonne
- efederici/capybara-claude-15k-ita by @efederici
๐ Thanks to the authors for the datasets.
๐ฏ Targeted training with Spectrum
I used Spectrum, a relatively new technique for parameter-efficient learning.
The idea is to train only the layers of the model with high Signal-to-Noise Ratio (SNR) and โ๏ธ freeze the rest.
I trained the top 30% of model layers.
๐ Spectrum paper: https://arxiv.org/abs/2406.06623
๐ Vibe check and performance on Italian benchmarks seem encouraging
- 2 replies
reacted to
Xenova's
post with ๐ฅ
5 months ago
Post
13945
I can't believe this... Phi-3.5-mini (3.8B) running in-browser at ~90 tokens/second on WebGPU w/ Transformers.js and ONNX Runtime Web! ๐คฏ Since everything runs 100% locally, no messages are sent to a server โ a huge win for privacy!
- ๐ค Demo: webml-community/phi-3.5-webgpu
- ๐งโ๐ป Source code: https://github.com/huggingface/transformers.js-examples/tree/main/phi-3.5-webgpu
- ๐ค Demo: webml-community/phi-3.5-webgpu
- ๐งโ๐ป Source code: https://github.com/huggingface/transformers.js-examples/tree/main/phi-3.5-webgpu
- 11 replies
liked
a
Space
7 months ago
updated
a
model
over 1 year ago
liked
a
model
about 3 years ago
liked
a
model
over 3 years ago
liked
a
Space
over 3 years ago