Some RLHF/RLVR experiments using GRPO and DPO.
Abdelaziz Bounhar
BounharAbdelaziz
AI & ML interests
Deep Learning, Reinforcement Learning, AI Agents, Generative Modeling, NLP, Information Theory, Security of Machine Learning, ...etc
Recent Activity
liked
a Space
about 5 hours ago
HuggingFaceTB/smol-training-playbook
liked
a dataset
about 9 hours ago
MBZUAI-Paris/Omni-MATH-Hard
published
a dataset
about 9 hours ago
MBZUAI-Paris/Omni-MATH-Hard
Organizations
Sentence and word embedding models for Moroccan darija (ary)
-
BounharAbdelaziz/ModernBERT-Morocco-Sentence-Embeddings-v0.2-bs-32-lr-2e-05-ep-2-wp-0.05-gacc-1-gnm-1.0-v0.3
Sentence Similarity • 0.2B • Updated • 1 -
BounharAbdelaziz/Morocco-Darija-Sentence-Embedding-v0.1
Feature Extraction • 0.6B • Updated • 3 • 2 -
BounharAbdelaziz/XLM-RoBERTa-Morocco-bs-32-lr-2e-05-ep-2-wp-0.05-gacc-1-gnm-1.0-v0.3
0.6B • Updated • 4 -
atlasia/Morocco-Darija-Word-Embedding
Feature Extraction • Updated • 3
A collection of all available datasets for pretraining LLMs
Language Models that speaks Moroccan darija (ary)
Moroccan darija STT
English to Moroccan darija (ary) models
-
BounharAbdelaziz/Terjman-v2-English-Morocco-Darija-Dataset-350K
Viewer • Updated • 355k • 9 • 1 -
BounharAbdelaziz/Terjman-Supreme-v2.0
Translation • 3B • Updated • 5 • 2 -
BounharAbdelaziz/Terjman-Ultra-v2.0
Translation • 1B • Updated • 4 • 2 -
BounharAbdelaziz/Terjman-Large-v2.0
Translation • 0.2B • Updated • 64 • 2
A collection of models (and the dataset used to train them) that are trained for summarizing arabic text.
-
BounharAbdelaziz/MaYofid-Qwen2.5-3B-Instruct
Text Generation • 3B • Updated • 3 -
BounharAbdelaziz/MaYofid-Falcon3-3B-Instruct
Text Generation • 3B • Updated -
BounharAbdelaziz/MaYofid-Qwen2.5-3B-Instruct-AWQ
0.7B • Updated • 1 -
BounharAbdelaziz/Arabic-Synthetic-Summarization-Dataset-Filtered
Viewer • Updated • 4.41k • 13 • 1
Some RLHF/RLVR experiments using GRPO and DPO.
Language Models that speaks Moroccan darija (ary)
Sentence and word embedding models for Moroccan darija (ary)
-
BounharAbdelaziz/ModernBERT-Morocco-Sentence-Embeddings-v0.2-bs-32-lr-2e-05-ep-2-wp-0.05-gacc-1-gnm-1.0-v0.3
Sentence Similarity • 0.2B • Updated • 1 -
BounharAbdelaziz/Morocco-Darija-Sentence-Embedding-v0.1
Feature Extraction • 0.6B • Updated • 3 • 2 -
BounharAbdelaziz/XLM-RoBERTa-Morocco-bs-32-lr-2e-05-ep-2-wp-0.05-gacc-1-gnm-1.0-v0.3
0.6B • Updated • 4 -
atlasia/Morocco-Darija-Word-Embedding
Feature Extraction • Updated • 3
Moroccan darija STT
A collection of all available datasets for pretraining LLMs
English to Moroccan darija (ary) models
-
BounharAbdelaziz/Terjman-v2-English-Morocco-Darija-Dataset-350K
Viewer • Updated • 355k • 9 • 1 -
BounharAbdelaziz/Terjman-Supreme-v2.0
Translation • 3B • Updated • 5 • 2 -
BounharAbdelaziz/Terjman-Ultra-v2.0
Translation • 1B • Updated • 4 • 2 -
BounharAbdelaziz/Terjman-Large-v2.0
Translation • 0.2B • Updated • 64 • 2
A collection of models (and the dataset used to train them) that are trained for summarizing arabic text.
-
BounharAbdelaziz/MaYofid-Qwen2.5-3B-Instruct
Text Generation • 3B • Updated • 3 -
BounharAbdelaziz/MaYofid-Falcon3-3B-Instruct
Text Generation • 3B • Updated -
BounharAbdelaziz/MaYofid-Qwen2.5-3B-Instruct-AWQ
0.7B • Updated • 1 -
BounharAbdelaziz/Arabic-Synthetic-Summarization-Dataset-Filtered
Viewer • Updated • 4.41k • 13 • 1