Running 98 The Eiffel Tower Llama π 98 Explore the Eiffel Tower Llama experiment with open-source models
Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability Collection A compilation of sparse auto-encoders trained on large language models. β’ 37 items β’ Updated 25 days ago β’ 20
ServiceNow-AI/Apriel-1.6-15b-Thinker Image-Text-to-Text β’ 15B β’ Updated 19 days ago β’ 8.71k β’ β’ 255
view post Post 3604 New family of 1B models just dropped!> LiquidAI/LFM2.5-1.2B-Base: 10T β 28T tokens> LiquidAI/LFM2.5-1.2B-Instruct: new large-scale multi-stage RL> LiquidAI/LFM2.5-1.2B-JP: our most polite model> LiquidAI/LFM2.5-VL-1.6B: multi-image multilingual> LiquidAI/LFM2.5-Audio-1.5B: 8x times faster, no quality lossSuper proud of this release π€ See translation 3 replies Β· π 14 14 + Reply
IQuestLab/IQuest-Coder-V1-40B-Instruct Text Generation β’ 40B β’ Updated 7 days ago β’ 5.55k β’ 262
IQuestLab/IQuest-Coder-V1-40B-Loop-Instruct Text Generation β’ 40B β’ Updated 3 days ago β’ 23k β’ 300