In a Training Loop 🔄

Stefano Fiorucci PRO

anakin87

AI & ML interests

Language Models: orchestration, post-training, GRPO, synthetic data... Contributing to Haystack LLM framework 🏗️

Recent Activity

reacted to theirpost with 🤗 about 7 hours ago

Local Gemma 4 agent 💎🕵️🗺️ drop in a mysterious map, get the location, live weather, and top spots to visit I've been exploring what https://huggingface.co/google/gemma-4-E4B-it can do in a local agentic setup and put together a 📓 𝙣𝙤𝙩𝙚𝙗𝙤𝙤𝙠 with Gemma + Haystack AI Framework covering 4 demos. 📓 https://t.ly/04Ty5 Another interesting one is the 𝗚𝗶𝘁𝗛𝘂𝗯 𝗔𝗴𝗲𝗻𝘁. I initially tried to load all tools from the GitHub MCP server, quickly filling the context available on Colab -> unusable, forgetful agent ❌ Then I used the 𝗦𝗲𝗮𝗿𝗰𝗵𝗮𝗯𝗹𝗲 𝗧𝗼𝗼𝗹𝘀𝗲𝘁 🔎 🧰 It dynamically discovers the right tools from the GitHub MCP server on the fly, loading only what it actually needs for the task at hand, keeping context lean. Now it actually works. The notebook also contains 💎 Multimodal weather agent: the mystery map demo above 💎 Visual Question Answering from a paper 💎 RAG on Rock music

posted an update about 7 hours ago

reacted to SeanLee97's post with 🔥 about 7 hours ago

Our lab recently released a paper where we introduce ShadowPEFT, a new Parameter-Efficient Fine-Tuning (PEFT) paradigm tailored for edge computing scenarios. Unlike traditional approaches such as LoRA and its variants, which inject trainable parameters directly into the weights of Transformer, requiring tight coupling with the backbone. ShadowPEFT instead enhances the frozen large base model by adding a lightweight, centralized, pretrainable, and detachable Shadow network. This shadow network operates in parallel with the base model, delivering learned corrections to each decoder layer. Because the shadow module is architecturally decoupled from the backbone, it can be independently trained, stored, and deployed, benefiting edge computing scenarios and edge-cloud collaboration computing. - HF Paper: https://huggingface.co/papers/2604.19254 - GitHub: https://github.com/ShadowLLM/shadow-peft - HF Collection: https://huggingface.co/collections/shadow-llm/shadow-peft-models

View all activity

Organizations

Posts 28

Post

Local Gemma 4 agent 💎🕵️🗺️
drop in a mysterious map, get the location, live weather, and top spots to visit

I've been exploring what google/gemma-4-E4B-it can do in a local agentic setup and put together a 📓 𝙣𝙤𝙩𝙚𝙗𝙤𝙤𝙠 with Gemma + Haystack AI Framework covering 4 demos.

📓 https://t.ly/04Ty5

Another interesting one is the 𝗚𝗶𝘁𝗛𝘂𝗯 𝗔𝗴𝗲𝗻𝘁.

I initially tried to load all tools from the GitHub MCP server, quickly filling the context available on Colab -> unusable, forgetful agent ❌

Then I used the 𝗦𝗲𝗮𝗿𝗰𝗵𝗮𝗯𝗹𝗲 𝗧𝗼𝗼𝗹𝘀𝗲𝘁 🔎 🧰
It dynamically discovers the right tools from the GitHub MCP server on the fly, loading only what it actually needs for the task at hand, keeping context lean.

Now it actually works.

The notebook also contains
💎 Multimodal weather agent: the mystery map demo above
💎 Visual Question Answering from a paper
💎 RAG on Rock music