Massimo Roberto Scamarcia PRO
mrs83
AI & ML interests
Natural Language Processing, Text Generation, Question Answering, Data Augmentation, Knowledge Transfer, Chain-of-Thought, ResearchOps, MLOps
Recent Activity
liked a model 3 days ago
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 liked a model 4 days ago
unsloth/Qwen3.8-27B-GGUF updated a Space 4 days ago
ethicalabs/echo-dsrn-openaire-clf-docsOrganizations
Posts 14
Post
143
A new classifier model for the OpenAIRE AI Hackathon 2026! 🇪🇺 it’s a 98M parameter Hybrid RNN that classifies research paper intents (Methodology, Dataset, Review, etc.) running entirely on CPU, currently classifying data from the OpenAIRE Graph API.
We are using a multi-model LLM-as-a-Judge pipeline to validate classifier’s predictions, but we need human experts to catch the edge cases.
Drop into the Collab Hub, review the classifications, and help us curate the open dataset for the upcoming v0.1.4 fine-tune!
Model card: ethicalabs/Echo-DSRN-v0.1.3-Research-Intent-CLF
Collab Hub: https://openaire-2026.ethicalabs.ai/
Made in 🇪🇺 with ❤️ for Open Science by
ethicalabs 🤗
We are using a multi-model LLM-as-a-Judge pipeline to validate classifier’s predictions, but we need human experts to catch the edge cases.
Drop into the Collab Hub, review the classifications, and help us curate the open dataset for the upcoming v0.1.4 fine-tune!
Model card: ethicalabs/Echo-DSRN-v0.1.3-Research-Intent-CLF
Collab Hub: https://openaire-2026.ethicalabs.ai/
Made in 🇪🇺 with ❤️ for Open Science by
Articles 2
Article
1
Fine-Tuning xLSTM-7B on a budget: An Experimental Journey with Chat Templates
Kurtis-EON1
- SleepingAgents
Kurtis EON1 Hybrid 0.7B
👁Qwen2.5 0.5B Transformers Backbone + Echo-DSRN (RNN)
-
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1
Text Generation • 0.7B • Updated • 281 -
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.0
Text Generation • 0.7B • Updated -
ethicalabs/Echo-DSRN-Qwen2.5-0.5B-Hybrid
Text Generation • 0.7B • Updated
Echo-DSRN 114M
O(1) memory RNN with surprise-gated dual-state learning
- Sleeping
Echo-DSRN 114M Telemetry 3D
🌌A 3D dashboard for the Echo-DSRN architecture
- SleepingAgents2
Echo-DSRN 114M SmolTools - Intent Classifier
⚡2🎙️ Multilingual Intent Classifier powered by Echo-DSRN-114M
- SleepingAgents2
Echo-DSRN-114M Semantic Compressor Demo (CPU)
🗜2Echo-DSRN-114M Semantic Compressor Demo (CPU)
- SleepingAgents
Echo DSRN Small Next Word Prediction
🔥Echo-DSRN-114M (114M RNN LM) - Next Word Prediction
Kurtis-EON1
- SleepingAgents
Kurtis EON1 Hybrid 0.7B
👁Qwen2.5 0.5B Transformers Backbone + Echo-DSRN (RNN)
-
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1
Text Generation • 0.7B • Updated • 281 -
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.0
Text Generation • 0.7B • Updated -
ethicalabs/Echo-DSRN-Qwen2.5-0.5B-Hybrid
Text Generation • 0.7B • Updated
Echo-DSRN 114M
O(1) memory RNN with surprise-gated dual-state learning
- Sleeping
Echo-DSRN 114M Telemetry 3D
🌌A 3D dashboard for the Echo-DSRN architecture
- SleepingAgents2
Echo-DSRN 114M SmolTools - Intent Classifier
⚡2🎙️ Multilingual Intent Classifier powered by Echo-DSRN-114M
- SleepingAgents2
Echo-DSRN-114M Semantic Compressor Demo (CPU)
🗜2Echo-DSRN-114M Semantic Compressor Demo (CPU)
- SleepingAgents
Echo DSRN Small Next Word Prediction
🔥Echo-DSRN-114M (114M RNN LM) - Next Word Prediction
spaces 5
Sleeping
Echo-DSRN CLF 3D Telemetry
🌌
3D telemetry for the Echo-DSRN research-intent classifier
Sleeping
Agents
Kurtis EON1 Hybrid 0.7B
👁
Qwen2.5 0.5B Transformers Backbone + Echo-DSRN (RNN)
Sleeping
ml-intern sandbox
🌍
Running
Huggingface Static 4d2f8c
🎯
Explore data with the interactive Trackio dashboard
Sleeping
Echo-DSRN 114M Telemetry 3D
🌌
A 3D dashboard for the Echo-DSRN architecture
models 15
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1
Text Generation • 0.7B • Updated • 281
mrs83/Kurtis-SmolLM2-1.7B-Instruct
Text Generation • 2B • Updated • 11
mrs83/Kurtis-SmolLM2-360M-Instruct
Text Generation • 0.4B • Updated • 13
mrs83/FlowerTune-Mistral-7B-Instruct-v0.3-Medical-PEFT
Text Generation • Updated • 6
mrs83/Kurtis-SmolLM2-1.7B-Instruct-DPO-PEFT
Updated
mrs83/Kurtis-SmolLM2-360M-Instruct-DPO-PEFT
Text Generation • Updated • 6
mrs83/FlowerTune-Qwen2.5-7B-Instruct-Medical-PEFT
Text Generation • Updated • 20 • 1
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.0
Text Generation • 0.7B • Updated
mrs83/Kurtis-EON1-Hybrid-2B-v0.1.2
Text Generation • 2B • Updated • 569
mrs83/Kurtis-SmolLM2-360M-Instruct-PEFT
Text Generation • Updated • 14
datasets 6
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1-vs-GPT-5.5
Viewer • Updated • 103 • 24
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1-vs-Gemma-4-26B-A4B-it
Viewer • Updated • 103 • 30
mrs83/kurtis_mental_health_dpo
Viewer • Updated • 2.8k • 8 • 4
mrs83/kurtis_mental_health_initial
Viewer • Updated • 11.5k • 17
mrs83/kurtis_mental_health_final
Viewer • Updated • 11.5k • 21 • 2
mrs83/kurtis_mental_health
Viewer • Updated • 4.5k • 17