LFM3-1.7B
Liquid AIThe final 3.5T tokens are a mid-training stage on curated data with a larger share of agentic traces and tool calls
3 more from this model
with a larger share of agentic traces and diverse tool calls to prepare the model for agentic post-training.
the last 3.5T tokens use curated, higher-quality data with a larger share of agentic traces and tool calls
the last 3.5T tokens use curated, higher-quality data with a larger share of agentic traces and tool calls