LFM2.5 2.6B model competitive with 4x larger models

(huggingface.co)

25 points | by nateb2022 6 days ago

3 comments

  • lend000 28 minutes ago
    I can't imagine who is using something like this for agentic coding, but I see exciting opportunities on the horizon when we can have hundreds of reasonably rational and conversational agents working on local machines to simulate emergent behavior (simulating crowds, markets, ecosystems, game NPCs, etc.)
  • Gecko4072 57 minutes ago
    These LiquidAI models have never worked well for me in practice.
    • eurekin 14 minutes ago
      Care to share any details? I'm about to check the 2.6b lfm on document editing.
  • 0xbadcafebee 16 minutes ago
    LFM's training/post-training is famously different than other models. They target reliable operation of tiny models in ways other model families don't (they aren't just scaling a larger model to a smaller size). If you're looking for good performance out of tiny models, LFM has the most advanced design.

    Note how they're much smaller than all other models in the comparison yet match or exceed them. This is for 2.6B params, but they have models as small as 230M. Nobody else designs models that small.