Meaningful leaderboards showcasing LLM evaluation results across various tasks and dimensions
Sara Han Díaz
sdiazlor
AI & ML interests
Data curation and generation, RLHF, RAG, Prompt Engineering
Recent Activity
upvoted an article about 1 month ago
How Pruna Optimizes Models: Tracing the Smash Function and DAG Execution updated a model 3 months ago
PrunaAI/flux2-klein-4b-smashed published a model 3 months ago
PrunaAI/flux2-klein-4b-smashedOrganizations
-
ChatDOC/OCRFlux-3B
Image-Text-to-Text • 4B • Updated • 1.27k • 369 -
allenai/olmOCR-7B-0225-preview
Image-Text-to-Text • 8B • Updated • 2.38k • 707 -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • 12B • Updated • 212k • • 2.74k -
Wan-AI/Wan2.1-T2V-14B
Text-to-Video • 14B • Updated • 64.7k • • 1.54k
A set of tools to preprocess, generate and curate data.
Popular instruction models to be run with Inference Endpoints
-
meta-llama/Llama-3.2-1B-Instruct
Text Generation • 1B • Updated • 10.4M • • 1.54k -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 2.04M • • 2.36k -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • 71B • Updated • 703k • • 2.92k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 8.37M • • 6.38k
Meaningful leaderboards showcasing LLM evaluation results across various tasks and dimensions
Popular instruction models to be run with Inference Endpoints
-
meta-llama/Llama-3.2-1B-Instruct
Text Generation • 1B • Updated • 10.4M • • 1.54k -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 2.04M • • 2.36k -
meta-llama/Llama-3.3-70B-Instruct
Text Generation • 71B • Updated • 703k • • 2.92k -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 8.37M • • 6.38k
-
ChatDOC/OCRFlux-3B
Image-Text-to-Text • 4B • Updated • 1.27k • 369 -
allenai/olmOCR-7B-0225-preview
Image-Text-to-Text • 8B • Updated • 2.38k • 707 -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • 12B • Updated • 212k • • 2.74k -
Wan-AI/Wan2.1-T2V-14B
Text-to-Video • 14B • Updated • 64.7k • • 1.54k
A set of tools to preprocess, generate and curate data.