NB
AI & ML interests
Recent Activity
Organizations
-
facebook/mbart-large-50-many-to-many-mmt
Translation β’ 0.6B β’ Updated β’ 153k β’ β’ 406 -
Helsinki-NLP/opus-mt-en-sw
Translation β’ Updated β’ 3.28k β’ β’ 7 -
facebook/seamless-m4t-v2-large
Automatic Speech Recognition β’ 2B β’ Updated β’ 90.8k β’ 967 -
facebook/seamless-streaming
Text-to-Speech β’ Updated β’ 281
- Paused3
Talk to Sambanova
π»3Llama 3.2 - SambaNova API
- Runtime error4
Whisper Realtime Transcription (Gradio UI)
π4Transcribe audio in realtime - Gradio UI version
- Runtime error1
LLM Voice Chat (Gradio)
π»1LLM Voice by ElevenLabs (Gradio)
- Runtime error1
Phonic AI Chat
π1Talk to Phonic AI's speech-to-speech model
-
unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF
33B β’ Updated β’ 35.6k β’ 146 -
unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF
Text Generation β’ 2B β’ Updated β’ 91k β’ 133 -
unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF
Text Generation β’ 8B β’ Updated β’ 38.1k β’ 294 - PausedFeatured670
Open Deep-Research
π670OpenAI's Deep Research, but open
-
fka/prompts.chat
Viewer β’ Updated β’ 1.6k β’ 31.9k β’ 9.63k -
Andyrasika/awesome_prompts
Viewer β’ Updated β’ 153 β’ 14 β’ 2 -
Skier8402/prompt-garden
Viewer β’ Updated β’ 21 β’ 29 β’ 2 -
Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)
Paper β’ 2510.04950 β’ Published β’ 1
- Runtime errorFeatured198
Better Florence 2
π₯198Analyze images to detect objects, generate captions, or perform OCR
- Runtime error34
EfficientSAM vs SAM
β34 - Runtime error31
Llava Interleave
π31Generate answers by uploading images or videos
- Running on Zero1.79k
DALLE 3 XL v2
π₯1.79kGenerate highβquality images from text prompts
- Running1
Detr Interp Space
π1DETR with GradCAM, IG & MC Drop Uncertanity Prediction
- Sleeping
GPT Interp Captum
πIntegrated gradients with Captum
- Sleeping
ViT Timm Interp
πViT online & Custom with LIME
- Running142
Semantic Galaxy
π142Visualize embeddings in 3D space, powered by EmbeddingGemma
- PausedFeatured56
Holo1 Navigation
π56Web Navigation powered by Holo1 Vision-Language Action Model
- Build error34
Holo1 Localization
π34Web Localization powered by Holo1
-
Hcompany/Holo1-3B
Image-Text-to-Text β’ 4B β’ Updated β’ 303 β’ 83 - PausedFeatured984
Computer Agent
π₯984Interact with an AI agent to perform web tasks
- Running on CPU Upgrade446
Agent Leaderboard
π¬446Ranking of LLMs for agentic tasks
- Building on CPU Upgrade7.22k
MTEB Leaderboard
π₯7.22kEmbedding Leaderboard
- Running on CPU Upgrade13.9k
Open LLM Leaderboard
π13.9kTrack, rank and evaluate open LLMs and chatbots
- Running4.81k
Arena Leaderboard
π4.81kView the LMArena language model leaderboard
- Running
MeshGPT
πGenerate 3D models from text descriptions
- Paused3.24k
Hunyuan3D-2.0
π3.24kText-to-3D and Image-to-3D Generation
- Running on ZeroFeatured4.78k
TRELLIS
π’4.78kScalable and Versatile 3D Generation from images
- PausedFeatured2.13k
Hunyuan3D-2.1
π»2.13kImage-to-3D Generation
-
MoritzLaurer/ModernBERT-base-zeroshot-v2.0
Text Classification β’ 0.1B β’ Updated β’ 885 β’ 19 -
nomic-ai/modernbert-embed-base
Sentence Similarity β’ Updated β’ 170k β’ 228 -
jxm/cde-small-v2
Feature Extraction β’ Updated β’ 21.6k β’ 90 -
BAAI/bge-m3
Sentence Similarity β’ Updated β’ 14.7M β’ β’ 2.89k
-
gpt-omni/mini-omni2
Any-to-Any β’ Updated β’ 57 β’ 283 -
vikhyatk/moondream2
Image-Text-to-Text β’ 2B β’ Updated β’ 3.37M β’ 1.4k - RunningFeatured37
Candle Moondream 2
π―37MoonDream 2 Vision Model on the Browser: Candle/Rust/WASM
- Running442
moondream2
π442a tiny vision language model
- Building on CPU Upgrade7.22k
MTEB Leaderboard
π₯7.22kEmbedding Leaderboard
- Running on CPU Upgrade13.9k
Open LLM Leaderboard
π13.9kTrack, rank and evaluate open LLMs and chatbots
- Running on CPU UpgradeFeatured1.01k
Model Memory Utility
π1.01kCalculate VRAM needed to train and run Hugging Face models
- Running on CPU UpgradeFeatured1.3k
Open ASR Leaderboard
π1.3kExplore speech model benchmarks and request new evaluations
- Runtime errorFeatured428
LLaVA
π₯428Chat with an AI assistant using text and images
- Runtime error2.04k
Stable Diffusion XL on TPUv5e
π2.04kGenerate images from text prompts
- Running on A10GFeatured601
Unofficial SDXL Turbo Img2Img Txt2Img
π¬601Generate images from text or an input picture
- Running on CPU Upgrade165
CogVLM
π165Answer questions about uploaded images using natural language
- Running1
Detr Interp Space
π1DETR with GradCAM, IG & MC Drop Uncertanity Prediction
- Sleeping
GPT Interp Captum
πIntegrated gradients with Captum
- Sleeping
ViT Timm Interp
πViT online & Custom with LIME
- Running142
Semantic Galaxy
π142Visualize embeddings in 3D space, powered by EmbeddingGemma
-
facebook/mbart-large-50-many-to-many-mmt
Translation β’ 0.6B β’ Updated β’ 153k β’ β’ 406 -
Helsinki-NLP/opus-mt-en-sw
Translation β’ Updated β’ 3.28k β’ β’ 7 -
facebook/seamless-m4t-v2-large
Automatic Speech Recognition β’ 2B β’ Updated β’ 90.8k β’ 967 -
facebook/seamless-streaming
Text-to-Speech β’ Updated β’ 281
- PausedFeatured56
Holo1 Navigation
π56Web Navigation powered by Holo1 Vision-Language Action Model
- Build error34
Holo1 Localization
π34Web Localization powered by Holo1
-
Hcompany/Holo1-3B
Image-Text-to-Text β’ 4B β’ Updated β’ 303 β’ 83 - PausedFeatured984
Computer Agent
π₯984Interact with an AI agent to perform web tasks
- Paused3
Talk to Sambanova
π»3Llama 3.2 - SambaNova API
- Runtime error4
Whisper Realtime Transcription (Gradio UI)
π4Transcribe audio in realtime - Gradio UI version
- Runtime error1
LLM Voice Chat (Gradio)
π»1LLM Voice by ElevenLabs (Gradio)
- Runtime error1
Phonic AI Chat
π1Talk to Phonic AI's speech-to-speech model
- Running on CPU Upgrade446
Agent Leaderboard
π¬446Ranking of LLMs for agentic tasks
- Building on CPU Upgrade7.22k
MTEB Leaderboard
π₯7.22kEmbedding Leaderboard
- Running on CPU Upgrade13.9k
Open LLM Leaderboard
π13.9kTrack, rank and evaluate open LLMs and chatbots
- Running4.81k
Arena Leaderboard
π4.81kView the LMArena language model leaderboard
- Running
MeshGPT
πGenerate 3D models from text descriptions
- Paused3.24k
Hunyuan3D-2.0
π3.24kText-to-3D and Image-to-3D Generation
- Running on ZeroFeatured4.78k
TRELLIS
π’4.78kScalable and Versatile 3D Generation from images
- PausedFeatured2.13k
Hunyuan3D-2.1
π»2.13kImage-to-3D Generation
-
unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF
33B β’ Updated β’ 35.6k β’ 146 -
unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF
Text Generation β’ 2B β’ Updated β’ 91k β’ 133 -
unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF
Text Generation β’ 8B β’ Updated β’ 38.1k β’ 294 - PausedFeatured670
Open Deep-Research
π670OpenAI's Deep Research, but open
-
MoritzLaurer/ModernBERT-base-zeroshot-v2.0
Text Classification β’ 0.1B β’ Updated β’ 885 β’ 19 -
nomic-ai/modernbert-embed-base
Sentence Similarity β’ Updated β’ 170k β’ 228 -
jxm/cde-small-v2
Feature Extraction β’ Updated β’ 21.6k β’ 90 -
BAAI/bge-m3
Sentence Similarity β’ Updated β’ 14.7M β’ β’ 2.89k
-
gpt-omni/mini-omni2
Any-to-Any β’ Updated β’ 57 β’ 283 -
vikhyatk/moondream2
Image-Text-to-Text β’ 2B β’ Updated β’ 3.37M β’ 1.4k - RunningFeatured37
Candle Moondream 2
π―37MoonDream 2 Vision Model on the Browser: Candle/Rust/WASM
- Running442
moondream2
π442a tiny vision language model
- Building on CPU Upgrade7.22k
MTEB Leaderboard
π₯7.22kEmbedding Leaderboard
- Running on CPU Upgrade13.9k
Open LLM Leaderboard
π13.9kTrack, rank and evaluate open LLMs and chatbots
- Running on CPU UpgradeFeatured1.01k
Model Memory Utility
π1.01kCalculate VRAM needed to train and run Hugging Face models
- Running on CPU UpgradeFeatured1.3k
Open ASR Leaderboard
π1.3kExplore speech model benchmarks and request new evaluations
-
fka/prompts.chat
Viewer β’ Updated β’ 1.6k β’ 31.9k β’ 9.63k -
Andyrasika/awesome_prompts
Viewer β’ Updated β’ 153 β’ 14 β’ 2 -
Skier8402/prompt-garden
Viewer β’ Updated β’ 21 β’ 29 β’ 2 -
Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)
Paper β’ 2510.04950 β’ Published β’ 1
- Runtime errorFeatured428
LLaVA
π₯428Chat with an AI assistant using text and images
- Runtime error2.04k
Stable Diffusion XL on TPUv5e
π2.04kGenerate images from text prompts
- Running on A10GFeatured601
Unofficial SDXL Turbo Img2Img Txt2Img
π¬601Generate images from text or an input picture
- Running on CPU Upgrade165
CogVLM
π165Answer questions about uploaded images using natural language
- Runtime errorFeatured198
Better Florence 2
π₯198Analyze images to detect objects, generate captions, or perform OCR
- Runtime error34
EfficientSAM vs SAM
β34 - Runtime error31
Llava Interleave
π31Generate answers by uploading images or videos
- Running on Zero1.79k
DALLE 3 XL v2
π₯1.79kGenerate highβquality images from text prompts