Ituria
🏃
16
Perform advanced searches using AI-driven models
Sivan Ratson
sivan22
AI & ML interests
Tora study improvement through Rabbinic Hebrew NLP, Semantic search, and OCR.
Recent Activity
updated
a Space
about 2 months ago
sivan22/Ituria
liked
a Space
3 months ago
khang119966/DeepSeek-OCR-DEMO
new activity
4 months ago
sivan22/Ituria:Contact
Organizations
updated
a
Space
about 2 months ago
liked
a
Space
3 months ago
embeddings (sentence similraity)
1
#5 opened 7 months ago
by
sivan22
liked
a
Space
9 months ago
upvoted
a
collection
12 months ago
updated
3
Spaces
about 1 year ago
liked
a
Space
about 1 year ago
reacted to
fdaudens's
post with 🔥
over 1 year ago
Post
3343
Small models, BIG impact: SmolLM is here! 🚀🔬
We're launching a series of small but mighty language models:
🏎️ Super fast - runs on laptops, phones, you name it!
📏 3 sizes: 130M, 350M, and 1.5B parameters
🥇 Outperforms same size models from Meta, Microsoft, and Qwen
🔓 Fully open-source: datasets, training code, models
𝐊𝐞𝐲 𝐟𝐞𝐚𝐭𝐮𝐫𝐞𝐬
- Trained on FineWeb-Edu and Cosmopedia v2 (largest synthetic pre-training dataset)
- No cloud needed - run locally for privacy and energy efficiency
- Everything is public, from data curation to training steps
𝐏𝐨𝐭𝐞𝐧𝐭𝐢𝐚𝐥 𝐮𝐬𝐞 𝐜𝐚𝐬𝐞𝐬
- On-device autocomplete
- Local request parsing
- Custom fine-tuning for specific needs without the need for expensive GPUs
𝐆𝐨 𝐝𝐞𝐞𝐩𝐞𝐫
👉 Check it out: https://huggingface.co/collections/HuggingFaceTB/smollm-models-6695016cad7167254ce15966
👉 Run the 360M model in your browser, 100 % private: HuggingFaceTB/SmolLM-360M-Instruct-WebGPU
👉 Read the blog explaining everything in detail: huggingface.co/blog/smollm
Kudos to the stellar team who worked on this project: @loubnabnl @anton-l @eliebak @lvwerra
We're launching a series of small but mighty language models:
🏎️ Super fast - runs on laptops, phones, you name it!
📏 3 sizes: 130M, 350M, and 1.5B parameters
🥇 Outperforms same size models from Meta, Microsoft, and Qwen
🔓 Fully open-source: datasets, training code, models
𝐊𝐞𝐲 𝐟𝐞𝐚𝐭𝐮𝐫𝐞𝐬
- Trained on FineWeb-Edu and Cosmopedia v2 (largest synthetic pre-training dataset)
- No cloud needed - run locally for privacy and energy efficiency
- Everything is public, from data curation to training steps
𝐏𝐨𝐭𝐞𝐧𝐭𝐢𝐚𝐥 𝐮𝐬𝐞 𝐜𝐚𝐬𝐞𝐬
- On-device autocomplete
- Local request parsing
- Custom fine-tuning for specific needs without the need for expensive GPUs
𝐆𝐨 𝐝𝐞𝐞𝐩𝐞𝐫
👉 Check it out: https://huggingface.co/collections/HuggingFaceTB/smollm-models-6695016cad7167254ce15966
👉 Run the 360M model in your browser, 100 % private: HuggingFaceTB/SmolLM-360M-Instruct-WebGPU
👉 Read the blog explaining everything in detail: huggingface.co/blog/smollm
Kudos to the stellar team who worked on this project: @loubnabnl @anton-l @eliebak @lvwerra
liked
a
Space
over 1 year ago
updated
a
Space
over 1 year ago
updated
a
dataset
over 1 year ago
Librarian Bot: Add language metadata for dataset
#1 opened over 1 year ago
by
librarian-bot
Librarian Bot: Add language metadata for dataset
#1 opened over 1 year ago
by
librarian-bot
updated
2
datasets
over 1 year ago
liked
a
model
over 1 year ago
