-
The Ultra-Scale Playbook
🌌3.61kThe ultimate guide to training LLM on large GPU Clusters
-
The Smol Training Playbook
📚2.75kThe secrets to building world-class LLMs
-
Evaluation Guidebook
📝218Display benchmark evaluation data for LLMs
-
FineVision: Open Data is All You Need
📝214A new open-source dataset for training VLMs
Sergio Paniego PRO
AI & ML interests
Recent Activity
Organizations
-
Sleeping41
comparevlms
🏃41Compare Vision Language Models
-
Runtime error4
Gemma3 License Plate Detection
📈4Gemma 3 for license plate detection
-
Running on ZeroFeatured141
Gemma 3n E4B It
⚡141Generate text responses to images, videos, and audio
-
Running on ZeroFeatured34
Moondream3
🏢34Image and video tasks with moondream3.
-
Sleeping41
comparevlms
🏃41Compare Vision Language Models
-
Running on Zero66
OCR Time Machine
📚66Extract text from images and XML files using OCR models
-
Running26
Compare Docvqa Models
🦀26Compare different visual question answering
-
Running on CPU Upgrade23
Compare Clip Siglip
🏃23Compare strong zero-shot image classification models
-
Qwen/Qwen2.5-Omni-7B
Any-to-Any • 11B • Updated • 160k • 1.83k -
RunningFeatured365
Qwen2.5 Omni 7B Demo
🏆365Generate text and speech responses from text, audio, images, or video input
-
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 168 -
openbmb/MiniCPM-o-2_6
Any-to-Any • 9B • Updated • 95.3k • 1.27k
-
Running3.61k
The Ultra-Scale Playbook
🌌3.61kThe ultimate guide to training LLM on large GPU Clusters
-
Running on CPU UpgradeFeatured2.75k
The Smol Training Playbook
📚2.75kThe secrets to building world-class LLMs
-
Running218
Evaluation Guidebook
📝218Display benchmark evaluation data for LLMs
-
Running214
FineVision: Open Data is All You Need
📝214A new open-source dataset for training VLMs
-
Sleeping41
comparevlms
🏃41Compare Vision Language Models
-
Running on Zero66
OCR Time Machine
📚66Extract text from images and XML files using OCR models
-
Running26
Compare Docvqa Models
🦀26Compare different visual question answering
-
Running on CPU Upgrade23
Compare Clip Siglip
🏃23Compare strong zero-shot image classification models
-
Sleeping41
comparevlms
🏃41Compare Vision Language Models
-
Runtime error4
Gemma3 License Plate Detection
📈4Gemma 3 for license plate detection
-
Running on ZeroFeatured141
Gemma 3n E4B It
⚡141Generate text responses to images, videos, and audio
-
Running on ZeroFeatured34
Moondream3
🏢34Image and video tasks with moondream3.
-
Qwen/Qwen2.5-Omni-7B
Any-to-Any • 11B • Updated • 160k • 1.83k -
RunningFeatured365
Qwen2.5 Omni 7B Demo
🏆365Generate text and speech responses from text, audio, images, or video input
-
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 168 -
openbmb/MiniCPM-o-2_6
Any-to-Any • 9B • Updated • 95.3k • 1.27k