Hugging Face's logo
Sharyar Naseem's picture
🔄 In a Training Loop

Sharyar Naseem

Snaseem2026
14 21 26
webxos's profile picture Gipsy727's profile picture Effsee44's profile picture
·

AI & ML interests

DevOps, CI/CD, AIOps, Code Analysis, Automation, Incident Response, MLOps, Local LLMs

Recent Activity

upvoted an article about 7 hours ago
Hugging Face Models on Foundry Managed Compute
reacted to sergiopaniego's post with 🤗 about 8 hours ago
LFM2.5-2.6B just dropped! and the @liquidai blog comes with some nice details about the training procedure, so let's analyze it. basically, a full agent training pipeline but compressed into 2.6B base model → SFT → specialized teachers per domain (SFT + RLVR) → on-policy distillation back into one student → agentic RL the two most interesting stages → MOPD: the student generates, each prompt routes to its domain teacher for token-level feedback. teachers branch from the same SFT checkpoint, so their signal stays close to the student's distribution → agentic RL: multi-turn GRPO inside real harnesses (OpenClaw, Hermes Agent), one sandbox per rollout, a proxy captures token-level trajectories while the harness stays a black box this makes a 2.6B that beats much larger models on instruction following and tool use SFT, distillation, RL, RL envs: exactly what we're covering in our Training Agents livestream series (next one coming soon!) → model: https://huggingface.co/LiquidAI/LFM2.5-2.6B → blog: https://www.liquid.ai/blog/lfm2-5-2-6b → live series: https://www.youtube.com/playlist?list=PLo2EIpI_JMQvQZm-kVlz4wY1vWF0LBcf5
upvoted an article about 8 hours ago
Security incident disclosure — July 2026
View all activity

Organizations

Open-Source AI Meetup's profile picture