LiquidAI/ lfm2.5-1.2b-instruct:latest

8,443 5 months ago

Blazingly fast 1.2B local AI chat model for on-device conversations, RAG, and tool calling.

... /
params
b78c4f81b658 · 138B
{
"repeat_penalty": 1.05,
"stop": [
"<|im_start|>",
"<|im_end|>",
"<|startoftext|>"
],
"temperature": 0.1,
"top_k": 50
}