PEFT-compatible LoRA adapters produced by mergekit-extract-lora
Xuan-Son Nguyen
ngxson
AI & ML interests
Doing AI for fun, not for profit
Recent Activity
upvoted an article 1 day ago
Transformers now runs llama.cpp quants liked a Space 5 days ago
pngwn/open-jevOrganizations
My first trial to make reasoning models
-
Llama 3.2 Reasoning WebGPU
🧠231Small and powerful reasoning LLM that runs in your browser
-
ngxson/MiniThinky-v2-1B-Llama-3.2
Text Generation • 1B • Updated • 194 • 43 -
ngxson/MiniThinky-v2-1B-Llama-3.2-Q8_0-GGUF
1B • Updated • 31 • 8 -
ngxson/MiniThinky-1B-Llama-3.2
Text Generation • 1B • Updated • 30 • 4
PEFT-compatible LoRA adapters produced by mergekit-extract-lora
My first trial to make reasoning models
-
Llama 3.2 Reasoning WebGPU
🧠231Small and powerful reasoning LLM that runs in your browser
-
ngxson/MiniThinky-v2-1B-Llama-3.2
Text Generation • 1B • Updated • 194 • 43 -
ngxson/MiniThinky-v2-1B-Llama-3.2-Q8_0-GGUF
1B • Updated • 31 • 8 -
ngxson/MiniThinky-1B-Llama-3.2
Text Generation • 1B • Updated • 30 • 4