Deep guides to do amazing things
NB
Skier8402
AI & ML interests
Explainable Computer Vision w/ Mech Interpretability, Optimization, NLP and multimodal system implementation.
Recent Activity
upvoted a changelog 2 days ago
Introducing Buckets: S3-like storage on the Hub liked
a model 6 days ago
huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated updated
a collection
11 days ago
3Dmodels Organizations
-
facebook/mbart-large-50-many-to-many-mmt
Translation β’ 0.6B β’ Updated β’ 94.9k β’ β’ 405 -
Helsinki-NLP/opus-mt-en-sw
Translation β’ Updated β’ 8.86k β’ β’ 7 -
facebook/seamless-m4t-v2-large
Automatic Speech Recognition β’ 2B β’ Updated β’ 86.1k β’ 962 -
facebook/seamless-streaming
Text-to-Speech β’ Updated β’ 280
-
unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF
33B β’ Updated β’ 21k β’ 146 -
unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF
Text Generation β’ 2B β’ Updated β’ 50.8k β’ 134 -
unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF
Text Generation β’ 8B β’ Updated β’ 51.3k β’ 296 -
Open Deep-Research
π670OpenAI's Deep Research, but open
a couple of controlnets to improve various aspects of an images
Agents that use user data to answer questions.
Interesting system prompts for different use cases.
-
fka/prompts.chat
Viewer β’ Updated β’ 1.45k β’ 23k β’ 9.61k -
Andyrasika/awesome_prompts
Viewer β’ Updated β’ 153 β’ 19 β’ 2 -
Skier8402/prompt-garden
Viewer β’ Updated β’ 21 β’ 90 β’ 2 -
Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)
Paper β’ 2510.04950 β’ Published β’ 1
A combination of chatbots and autonomous agents that answer questions based on user input.
Image and video models
Opening the hood of Computer Vision model for example ResNets, ConvNext & DETR, multimodal models and NLP models:BERT & GPTs.
Text to 3D models
-
MoritzLaurer/ModernBERT-base-zeroshot-v2.0
Text Classification β’ 0.1B β’ Updated β’ 769 β’ 19 -
nomic-ai/modernbert-embed-base
Sentence Similarity β’ Updated β’ 337k β’ 227 -
jxm/cde-small-v2
Feature Extraction β’ Updated β’ 25.7k β’ 90 -
BAAI/bge-m3
Sentence Similarity β’ Updated β’ 17.4M β’ β’ 2.83k
Leaderboards on embeddings, open source LLMs, approximating memory constraints, and Automatic speech recognition.
-
MTEB Leaderboard
π₯7.13kEmbedding Leaderboard
-
Open LLM Leaderboard
π13.9kTrack, rank and evaluate open LLMs and chatbots
-
Model Memory Utility
π1.01kCalculate VRAM needed to train and run Hugging Face models
-
Open ASR Leaderboard
π1.24kExplore ASR model performance across languages and datasets
Various applications to help deal with speech better.
Very cool apps I wish I could build
-
LLaVA
π₯427Chat with an AI assistant using text and images
-
Stable Diffusion XL on TPUv5e
π2.04kGenerate images from text prompts
-
Unofficial SDXL Turbo Img2Img Txt2Img
π¬601Generate images from text or modify existing images
-
CogVLM
π165Answer questions about uploaded images using natural language
Interesting datasets to help train LLMs and beyond
This is a set of models that can help with data generation.
Deep guides to do amazing things
Opening the hood of Computer Vision model for example ResNets, ConvNext & DETR, multimodal models and NLP models:BERT & GPTs.
-
facebook/mbart-large-50-many-to-many-mmt
Translation β’ 0.6B β’ Updated β’ 94.9k β’ β’ 405 -
Helsinki-NLP/opus-mt-en-sw
Translation β’ Updated β’ 8.86k β’ β’ 7 -
facebook/seamless-m4t-v2-large
Automatic Speech Recognition β’ 2B β’ Updated β’ 86.1k β’ 962 -
facebook/seamless-streaming
Text-to-Speech β’ Updated β’ 280
Text to 3D models
-
unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF
33B β’ Updated β’ 21k β’ 146 -
unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF
Text Generation β’ 2B β’ Updated β’ 50.8k β’ 134 -
unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF
Text Generation β’ 8B β’ Updated β’ 51.3k β’ 296 -
Open Deep-Research
π670OpenAI's Deep Research, but open
-
MoritzLaurer/ModernBERT-base-zeroshot-v2.0
Text Classification β’ 0.1B β’ Updated β’ 769 β’ 19 -
nomic-ai/modernbert-embed-base
Sentence Similarity β’ Updated β’ 337k β’ 227 -
jxm/cde-small-v2
Feature Extraction β’ Updated β’ 25.7k β’ 90 -
BAAI/bge-m3
Sentence Similarity β’ Updated β’ 17.4M β’ β’ 2.83k
a couple of controlnets to improve various aspects of an images
Leaderboards on embeddings, open source LLMs, approximating memory constraints, and Automatic speech recognition.
-
MTEB Leaderboard
π₯7.13kEmbedding Leaderboard
-
Open LLM Leaderboard
π13.9kTrack, rank and evaluate open LLMs and chatbots
-
Model Memory Utility
π1.01kCalculate VRAM needed to train and run Hugging Face models
-
Open ASR Leaderboard
π1.24kExplore ASR model performance across languages and datasets
Agents that use user data to answer questions.
Various applications to help deal with speech better.
Interesting system prompts for different use cases.
-
fka/prompts.chat
Viewer β’ Updated β’ 1.45k β’ 23k β’ 9.61k -
Andyrasika/awesome_prompts
Viewer β’ Updated β’ 153 β’ 19 β’ 2 -
Skier8402/prompt-garden
Viewer β’ Updated β’ 21 β’ 90 β’ 2 -
Mind Your Tone: Investigating How Prompt Politeness Affects LLM Accuracy (short paper)
Paper β’ 2510.04950 β’ Published β’ 1
Very cool apps I wish I could build
-
LLaVA
π₯427Chat with an AI assistant using text and images
-
Stable Diffusion XL on TPUv5e
π2.04kGenerate images from text prompts
-
Unofficial SDXL Turbo Img2Img Txt2Img
π¬601Generate images from text or modify existing images
-
CogVLM
π165Answer questions about uploaded images using natural language
A combination of chatbots and autonomous agents that answer questions based on user input.
Interesting datasets to help train LLMs and beyond
This is a set of models that can help with data generation.
Image and video models