Mahmud ElHuseyni π΅πΈ
MElHuseyni
AI & ML interests
Computer Vision
NLP
Machine Learning
Recent Activity
liked
a Space
about 1 hour ago
Qwen/Qwen3-ASR-Demo
liked
a dataset
about 20 hours ago
tunis-ai/tunisian-msa-parallel-corpus-evaluated
authored
a paper
about 22 hours ago
Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG
Applications
Organizations
-
HuggingFaceTB/SmolVLM-Instruct
Image-Text-to-Text β’ 2B β’ Updated β’ 62.9k β’ 545 -
OpenGVLab/InternVL3-1B
Image-Text-to-Text β’ 0.9B β’ Updated β’ 88.1k β’ 74 -
OpenGVLab/InternVL3-2B
Image-Text-to-Text β’ 2B β’ Updated β’ 51k β’ 39 -
LiquidAI/LFM2-VL-450M
Image-Text-to-Text β’ 0.5B β’ Updated β’ 7.49k β’ 114
-
jinaai/jina-embeddings-v4
Visual Document Retrieval β’ 4B β’ Updated β’ 56k β’ 364 -
vidore/colqwen2.5-v0.2
Visual Document Retrieval β’ Updated β’ 136k β’ 78 -
nomic-ai/colnomic-embed-multimodal-7b
Visual Document Retrieval β’ Updated β’ 16.2k β’ 87 -
nvidia/llama-nemoretriever-colembed-3b-v1
Visual Document Retrieval β’ 4B β’ Updated β’ 2.2k β’ 46
-
ICTNLP/Llama-3.1-8B-Omni
9B β’ Updated β’ 489 β’ 412 -
AudioPaLM: A Large Language Model That Can Speak and Listen
Paper β’ 2306.12925 β’ Published β’ 55 -
fnlp/SpeechGPT-7B-cm
Text Generation β’ Updated β’ 91 β’ 7 -
parler-tts/parler_tts_mini_v0.1
Text-to-Speech β’ 0.6B β’ Updated β’ 15.6k β’ 356
-
nvidia/segformer-b5-finetuned-cityscapes-1024-1024
Image Segmentation β’ Updated β’ 119k β’ β’ 31 -
nvidia/segformer-b0-finetuned-ade-512-512
Image Segmentation β’ 0.0B β’ Updated β’ 339k β’ β’ 165 -
facebook/maskformer-swin-base-ade
Image Segmentation β’ Updated β’ 2.54k β’ β’ 13 -
facebook/maskformer-swin-base-coco
Image Segmentation β’ 0.1B β’ Updated β’ 1.41k β’ β’ 26
-
37
OCRBenchv2 Leaderboard
πDisplay OCRBench leaderboard for text recognition models
-
174
Vidore Leaderboard
π₯Explore visual document retrieval benchmark results
-
890
Open VLM Leaderboard
πVLMEvalKit Evaluation Results Collection
-
558
Vision Arena (Testing VLMs side-by-side)
πΌDisplay image analysis results
-
DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference
Paper β’ 2401.08671 β’ Published β’ 15 -
NanoFlow: Towards Optimal Large Language Model Serving Throughput
Paper β’ 2408.12757 β’ Published β’ 18 -
richard-park/llama3-deepspeed-v1.0
Text Generation β’ 8B β’ Updated β’ 7 β’ β’ 1
-
HuggingFaceTB/SmolVLM-Instruct
Image-Text-to-Text β’ 2B β’ Updated β’ 62.9k β’ 545 -
OpenGVLab/InternVL3-1B
Image-Text-to-Text β’ 0.9B β’ Updated β’ 88.1k β’ 74 -
OpenGVLab/InternVL3-2B
Image-Text-to-Text β’ 2B β’ Updated β’ 51k β’ 39 -
LiquidAI/LFM2-VL-450M
Image-Text-to-Text β’ 0.5B β’ Updated β’ 7.49k β’ 114
-
nvidia/segformer-b5-finetuned-cityscapes-1024-1024
Image Segmentation β’ Updated β’ 119k β’ β’ 31 -
nvidia/segformer-b0-finetuned-ade-512-512
Image Segmentation β’ 0.0B β’ Updated β’ 339k β’ β’ 165 -
facebook/maskformer-swin-base-ade
Image Segmentation β’ Updated β’ 2.54k β’ β’ 13 -
facebook/maskformer-swin-base-coco
Image Segmentation β’ 0.1B β’ Updated β’ 1.41k β’ β’ 26
-
jinaai/jina-embeddings-v4
Visual Document Retrieval β’ 4B β’ Updated β’ 56k β’ 364 -
vidore/colqwen2.5-v0.2
Visual Document Retrieval β’ Updated β’ 136k β’ 78 -
nomic-ai/colnomic-embed-multimodal-7b
Visual Document Retrieval β’ Updated β’ 16.2k β’ 87 -
nvidia/llama-nemoretriever-colembed-3b-v1
Visual Document Retrieval β’ 4B β’ Updated β’ 2.2k β’ 46
-
37
OCRBenchv2 Leaderboard
πDisplay OCRBench leaderboard for text recognition models
-
174
Vidore Leaderboard
π₯Explore visual document retrieval benchmark results
-
890
Open VLM Leaderboard
πVLMEvalKit Evaluation Results Collection
-
558
Vision Arena (Testing VLMs side-by-side)
πΌDisplay image analysis results
-
ICTNLP/Llama-3.1-8B-Omni
9B β’ Updated β’ 489 β’ 412 -
AudioPaLM: A Large Language Model That Can Speak and Listen
Paper β’ 2306.12925 β’ Published β’ 55 -
fnlp/SpeechGPT-7B-cm
Text Generation β’ Updated β’ 91 β’ 7 -
parler-tts/parler_tts_mini_v0.1
Text-to-Speech β’ 0.6B β’ Updated β’ 15.6k β’ 356
-
DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference
Paper β’ 2401.08671 β’ Published β’ 15 -
NanoFlow: Towards Optimal Large Language Model Serving Throughput
Paper β’ 2408.12757 β’ Published β’ 18 -
richard-park/llama3-deepspeed-v1.0
Text Generation β’ 8B β’ Updated β’ 7 β’ β’ 1