Hugging Face's logo
Clemente Henriquez's picture

Clemente Henriquez PRO

ClementeH
1 39 174
pcuenq's profile picture Lian52's profile picture Tuana's profile picture
·
https://clemente-h.github.io

AI & ML interests

None yet

Recent Activity

reacted to FredyRivera-dev's post with 👍 about 16 hours ago
I've written a technical blog post about how we create a multimodal model: Kairos: a multimodal model built with LFM2.5-2.6B as the LLM, MoonViT-3D (the vision tower of Kimi-K2.6) as the vision encoder, and a custom projector. The original plan was LLaVA's approach, two stages: first align the projector with the LLM frozen, and then train the projector + LLM together. The first stage worked in terms of loss (ablation with +3.7 nats in favor of the image), but in free generation the image shifted the logits without changing the argmax: the model received the image and ignored it. That's why we jumped directly to early fusion, with a reasoning dataset. For that, we created Kairos-Multimodal-Reasoning: 116,357 examples with explicit reasoning traces, generated through distillation (60,041 from LLaVA-CC3M, 2,295 from WebSight, and 54,021 from Zebra-CoT), with GPT 5.6 Luna, Inkling, Qwen 3.6 27B, and Qwen 3.7 Plus as teachers. The training, in two phases: 1. Projector through backbone with 80k image-text pairs (Kairos-Proj-80k). 2. Projector + LoRA (r=16) with 30k examples from the reasoning dataset (Kairos-Alig-30k). Everything is open source: - Full blog post with the process: https://aquiles-ai.vercel.app/blog/kairos-a-multimodal-model - Implementation: https://github.com/Aquiles-ai/Kairos To be honest: the checkpoints are not a competent model, they are experimental artifacts. But they validated the approach and precisely defined what the next iteration needs. https://huggingface.co/collections/Aquiles-ai/kairos https://huggingface.co/Aquiles-ai/MoonViT-3D https://huggingface.co/LiquidAI/LFM2.5-2.6B
upvoted a collection about 16 hours ago
Kairos
reacted to Banaxi-Tech's post with 🚀 2 days ago
We're releasing BananaMind 2.1 Unified, a 35M three-tower relay model where the two output towers can only talk to each other through a silent middle tower that has no output head and no loss term. Tower B trains entirely on indirect gradient. It was never told what to predict. It woke up anyway. Jacobian lens shows it carrying the correct answer ("Paris", "oxygen", "blue") at its deepest layer. Its bridge gates grew 4-47x from init. Feed it from only one side and the representations collapse to junk — it needs both outer towers to become semantic. The PIQA result is the cleanest demonstration: Tower A alone scores 50.11 (chance). Tower C alone 52.12. Full system 61.75. All physical reasoning lives in the integration. The 35M three-tower beats the 50M single-tower BananaMind 2 Medium on PIQA. Trained on 38B tokens in ~7.5 hours on 8x RTX PRO 6000. Ships with 7 ablation modes so you can surgically cut the model apart without retraining. Full training logs, J-lens fits, and eval outputs for every mode included. This is a research model. It is interesting because you can take it apart. https://huggingface.co/BananaMind/BananaMind-2.1-Unified Follow us for more: https://huggingface.co/BananaMind @Banaxi-Tech
View all activity

Organizations

CenIA's profile picture DCC UChile's profile picture SomosNLP's profile picture AI Developers from Latin America's profile picture LatamGPT's profile picture Hackathon SomosNLP 2025's profile picture Agents-MCP-Hackathon's profile picture MCP-1st-Birthday's profile picture Mistral Hack-a-ton 2026's profile picture Build Small Hackathon's profile picture ICML 2026 Agent Reproductions's profile picture