Creating your custom Ghibli Text-to-Image model
•
17
AtlasIA
community
AI & ML interests
Open-source data and models for Morocco.
Recent Activity
View all activity
Articles
AymaneElfirdo
updated
a
dataset
1 day ago
oumayma03
updated
a
Space
5 days ago
01Yassine
authored
12
papers
27 days ago
L1-aware Multilingual Mispronunciation Detection Framework
Paper
•
2309.07719
•
Published
SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation
Paper
•
2211.00923
•
Published
Automatic Pronunciation Assessment -- A Review
Paper
•
2310.13974
•
Published
BiCrossMamba-ST: Speech Deepfake Detection with Bidirectional Mamba Spectro-Temporal Cross-Attention
Paper
•
2505.13930
•
Published
Comprehensive Layer-wise Analysis of SSL Models for Audio Deepfake Detection
Paper
•
2502.03559
•
Published
Beyond Orthography: Automatic Recovery of Short Vowels and Dialectal Sounds in Arabic
Paper
•
2408.02430
•
Published
Speech Representation Analysis based on Inter- and Intra-Model Similarities
Paper
•
2406.16099
•
Published
The complementary roles of non-verbal cues for Robust Pronunciation Assessment
Paper
•
2309.07739
•
Published
Multi-View Multi-Task Representation Learning for Mispronunciation Detection
Paper
•
2306.01845
•
Published
MyVoice: Arabic Speech Resource Collaboration Platform
Paper
•
2308.02503
•
Published
QVoice: Arabic Speech Pronunciation Learning Application
Paper
•
2305.07445
•
Published
Towards a Unified Benchmark for Arabic Pronunciation Assessment: Quranic Recitation as Case Study
Paper
•
2506.07722
•
Published
alielfilali01
authored
a
paper
about 1 month ago
lekssays
authored
a
paper
about 2 months ago
alielfilali01
posted
an
update
2 months ago
Post
712
Great efforts from
@AtlasIA
folks to adapt text2image models (ghibli style) for Moroccan Context
Read the blog is here : https://huggingface.co/blog/atlasia/creating-your-custom-ghibli-text-to-image-model
Read the blog is here : https://huggingface.co/blog/atlasia/creating-your-custom-ghibli-text-to-image-model
nouamanetazi
authored
a
paper
3 months ago
alielfilali01
posted
an
update
5 months ago
Post
1050
🚨 Arabic LLM Evaluation 🚨
Few models join the ranking of https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard Today.
The new MistralAI model, Saba, is quite impressive, Top10 ! Well done @arthurmensch and team.
Sadly Mistral did not follow its strategy about public weights this time, we hope this changes soon and we get the model with a permissive license.
We added other Mistral models and apparently, we have been sleeping on mistralai/Mistral-Large-Instruct-2411 !
Another impressive model that joined the ranking today is ALLaM-AI/ALLaM-7B-Instruct-preview. After a long wait finally ALLaM is here and it is IMPRESSIVE given its size !
ALLaM is ranked on OALL/Open-Arabic-LLM-Leaderboard as well.
Few models join the ranking of https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard Today.
The new MistralAI model, Saba, is quite impressive, Top10 ! Well done @arthurmensch and team.
Sadly Mistral did not follow its strategy about public weights this time, we hope this changes soon and we get the model with a permissive license.
We added other Mistral models and apparently, we have been sleeping on mistralai/Mistral-Large-Instruct-2411 !
Another impressive model that joined the ranking today is ALLaM-AI/ALLaM-7B-Instruct-preview. After a long wait finally ALLaM is here and it is IMPRESSIVE given its size !
ALLaM is ranked on OALL/Open-Arabic-LLM-Leaderboard as well.
alielfilali01
posted
an
update
6 months ago
Post
2137
3C3H AraGen Leaderboard welcomes today
deepseek-ai/DeepSeek-V3 and 12 other models (including the late gpt-3.5 💀) to the ranking of best LLMs in Arabic !
Observations:
- DeepSeek-v3 ranked 3rd and only Open model among the top 5 !
- A 14B open model ( Qwen/Qwen2.5-14B-Instruct) outperforms gpt-3.5-turbo-0125 (from last year). This shows how much we came in advancing and supporting Arabic presence within the LLM ecosystem !
- Contrary to what observed in likelihood-acc leaderboards (like OALL/Open-Arabic-LLM-Leaderboard) further finetuned models like maldv/Qwentile2.5-32B-Instruct actually decreased the performance compared to the original model Qwen/Qwen2.5-32B-Instruct.
It's worth to note that the decrease is statiscally insignificant which imply that at best, the out-domain finetuning do not really hurts the model original capabilities acquired during pretraining.
Previous work addressed this (finetuning VS pretraining) but more investigation in this regard is required (any PhDs here ? This could be your question ...)
Check out the latest rankings: https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard
Observations:
- DeepSeek-v3 ranked 3rd and only Open model among the top 5 !
- A 14B open model ( Qwen/Qwen2.5-14B-Instruct) outperforms gpt-3.5-turbo-0125 (from last year). This shows how much we came in advancing and supporting Arabic presence within the LLM ecosystem !
- Contrary to what observed in likelihood-acc leaderboards (like OALL/Open-Arabic-LLM-Leaderboard) further finetuned models like maldv/Qwentile2.5-32B-Instruct actually decreased the performance compared to the original model Qwen/Qwen2.5-32B-Instruct.
It's worth to note that the decrease is statiscally insignificant which imply that at best, the out-domain finetuning do not really hurts the model original capabilities acquired during pretraining.
Previous work addressed this (finetuning VS pretraining) but more investigation in this regard is required (any PhDs here ? This could be your question ...)
Check out the latest rankings: https://huggingface.co/spaces/inceptionai/AraGen-Leaderboard