Alvaro Moran
@tengomucho.bsky.social
ML Engineer @ Hugging Face 🤗 - open source passionate, software developer
I love geeky advent calendars. Among them, this year I really like Hugging Face "Open-source AI: year in review 2024", check it out! huggingface.co/spaces/huggi...
Open Source Ai Year In Review 2024 - a Hugging Face Space by huggingface
What happened in open-source AI this year, and what’s next?
huggingface.co
December 12, 2024 at 9:19 AM
I love geeky advent calendars. Among them, this year I really like Hugging Face "Open-source AI: year in review 2024", check it out! huggingface.co/spaces/huggi...
Reposted by Alvaro Moran
Top organizations releasing open-source AI models over the course of 2024 (cumulative likes)
Interactive viz: huggingface-open-source-ai-year-in-review-2024.static.hf.space/index.html?d...
Discussion: huggingface.co/spaces/huggi...
Interactive viz: huggingface-open-source-ai-year-in-review-2024.static.hf.space/index.html?d...
Discussion: huggingface.co/spaces/huggi...
December 4, 2024 at 7:04 PM
Top organizations releasing open-source AI models over the course of 2024 (cumulative likes)
Interactive viz: huggingface-open-source-ai-year-in-review-2024.static.hf.space/index.html?d...
Discussion: huggingface.co/spaces/huggi...
Interactive viz: huggingface-open-source-ai-year-in-review-2024.static.hf.space/index.html?d...
Discussion: huggingface.co/spaces/huggi...
Reposted by Alvaro Moran
The EuroLLM
- 1.7B and 9B parameter
- 24 EU languages (11 non EU)
- 4 trillion pre-training tokens
- beating European alternatives like Mistral
- Comparable to Gemma-2 models (non-EU)
- Apache 2 license
- 👎 No dataset release
- 1.7B and 9B parameter
- 24 EU languages (11 non EU)
- 4 trillion pre-training tokens
- beating European alternatives like Mistral
- Comparable to Gemma-2 models (non-EU)
- Apache 2 license
- 👎 No dataset release
EuroLLM-9B
A Blog post by EuroLLM Team on Hugging Face
buff.ly
December 3, 2024 at 1:00 PM
The EuroLLM
- 1.7B and 9B parameter
- 24 EU languages (11 non EU)
- 4 trillion pre-training tokens
- beating European alternatives like Mistral
- Comparable to Gemma-2 models (non-EU)
- Apache 2 license
- 👎 No dataset release
- 1.7B and 9B parameter
- 24 EU languages (11 non EU)
- 4 trillion pre-training tokens
- beating European alternatives like Mistral
- Comparable to Gemma-2 models (non-EU)
- Apache 2 license
- 👎 No dataset release
I found this positional encoding blog post very good!
huggingface.co/blog/designi...
huggingface.co/blog/designi...
You could have designed state of the art positional encoding
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
November 27, 2024 at 9:37 AM
I found this positional encoding blog post very good!
huggingface.co/blog/designi...
huggingface.co/blog/designi...