owao

233 7 298

AI & ML interests

listen to the coil whine to tune draft-n

Recent Activity

new activity 2 days ago

meta-models/Muse-Glimmer-30B:K-Quant-17GB

liked a model 2 days ago

meta-models/Muse-Glimmer-30B-GGUF

liked a model 3 days ago

ShaoShuai0605/Harness-R1

View all activity

Organizations

New activity in meta-models/Muse-Glimmer-30B 2 days ago

K-Quant-17GB

#14 opened 2 days ago by

BuiDoan

liked a model 2 days ago

meta-models/Muse-Glimmer-30B-GGUF

Image-Text-to-Text • 28B • Updated 1 day ago • 228

liked 2 models 3 days ago

ShaoShuai0605/Harness-R1

Reinforcement Learning • Updated 11 days ago • 13

bartowski/endless-frontier_BigBang-v1-GGUF

Image-Text-to-Text • 36B • Updated 5 days ago • 7.45k • 24

replied to mlabonne's post 5 days ago

Oh there I have the explanation! Great thing to tailor it to your SLMs! Who can do less can do more! I always thought a great harness is the one SLMs are comfortable with, like an optimized code vs one counting on overpowered hardware to hide the flaws!
Long life to LFM!

reacted to mlabonne's post with 🚀 5 days ago

Post

3103

Deploy local agents everywhere with LiquidAI/LFM2.5-2.6B

Unlike agents that depend on cloud APIs, local agents give you free inference, low latency, and real privacy.

Removing the per-token cost changes how developers build: agents can now be massively parallelized on local hardware, running background tasks that burn through millions of tokens at no marginal cost!

7 replies

replied to mlabonne's post 6 days ago

Hey @mlabonne I'm curious about the client UI, which looks great! I tried searching online but couldn't figure out what we see here!
And congrat for the model!