Measuring What Matters: Objective Metrics for Image Generation Assessment
•
8
AI & ML interests
Efficient machine learning for any model and hardware: pruning, quantization, compilation, and more.
Recent Activity
View all activity
Articles
Many variations of Llama 3 with many compression techniques.
-
PrunaAI/Meta-Llama-3-70B-Instruct-GGUF-smashed
71B • Updated • 44 • 7 -
PrunaAI/dolphin-2.9-llama3-70b-GGUF-smashed
71B • Updated • 388 • 3 -
PrunaAI/llava-llama-3-8b-v1_1-GGUF-smashed
8B • Updated • 115 • 3 -
PrunaAI/gradientai-Llama-3-8B-Instruct-262k-AWQ-4bit-smashed
Text Generation • 2B • Updated • 21 • 4
Many variations of Gemma with many compression techniques.
Many variations of SmolLM2 with many variation techniques
-
PrunaAI/HuggingFaceTB-SmolLM2-1.7B-Instruct-AWQ-4bit-smashed
0.3B • Updated • 4 -
PrunaAI/HuggingFaceTB-SmolLM2-1.7B-Instruct-bnb-4bit-smashed
0.9B • Updated • 3 • 1 -
PrunaAI/HuggingFaceTB-SmolLM2-1.7B-Instruct-QUANTO-qint2bit-smashed
Updated • 4 -
PrunaAI/HuggingFaceTB-SmolLM2-1.7B-Instruct-QUANTO-qint4bit-smashed
Updated • 3
Many variations of Phi 3 with many compression techniques.
-
PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed
4B • Updated • 4.12k • 67 -
PrunaAI/Phi-3-mini-4k-instruct-GGUF-Imatrix-smashed
4B • Updated • 1.17k • 5 -
PrunaAI/microsoft-Phi-3-mini-4k-instruct-HQQ-2bit-smashed
Text Generation • Updated • 9 -
PrunaAI/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed
Text Generation • Updated • 11
Many variations of Llama 3 with many compression techniques.
-
PrunaAI/Meta-Llama-3-70B-Instruct-GGUF-smashed
71B • Updated • 44 • 7 -
PrunaAI/dolphin-2.9-llama3-70b-GGUF-smashed
71B • Updated • 388 • 3 -
PrunaAI/llava-llama-3-8b-v1_1-GGUF-smashed
8B • Updated • 115 • 3 -
PrunaAI/gradientai-Llama-3-8B-Instruct-262k-AWQ-4bit-smashed
Text Generation • 2B • Updated • 21 • 4
Many variations of Phi 3 with many compression techniques.
-
PrunaAI/Phi-3-mini-128k-instruct-GGUF-Imatrix-smashed
4B • Updated • 4.12k • 67 -
PrunaAI/Phi-3-mini-4k-instruct-GGUF-Imatrix-smashed
4B • Updated • 1.17k • 5 -
PrunaAI/microsoft-Phi-3-mini-4k-instruct-HQQ-2bit-smashed
Text Generation • Updated • 9 -
PrunaAI/microsoft-Phi-3-mini-128k-instruct-HQQ-4bit-smashed
Text Generation • Updated • 11
Many variations of Gemma with many compression techniques.
Many variations of SmolLM2 with many variation techniques
-
PrunaAI/HuggingFaceTB-SmolLM2-1.7B-Instruct-AWQ-4bit-smashed
0.3B • Updated • 4 -
PrunaAI/HuggingFaceTB-SmolLM2-1.7B-Instruct-bnb-4bit-smashed
0.9B • Updated • 3 • 1 -
PrunaAI/HuggingFaceTB-SmolLM2-1.7B-Instruct-QUANTO-qint2bit-smashed
Updated • 4 -
PrunaAI/HuggingFaceTB-SmolLM2-1.7B-Instruct-QUANTO-qint4bit-smashed
Updated • 3