mrs83/huggingface-static-62f6b6-bucket
0 Bytes
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 1 day ago
NX-AI/KronLSTM-1.5B-100B-32k liked a model 1 day ago
NX-AI/KronLSTM-1.5B-100B liked a dataset 4 days ago
Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120bOrganizations
Posts 16
Post
124
Currently HF Papers only ingests arXiv IDs. While arXiv is standard, it imposes endorsement requirements and legacy moderation bottlenecks that exclude a growing segment of independent researchers, decentralized collectives, and open-source practitioners who publish peer-traceable preprints through CERN/Zenodo, OpenAIRE or OSF.
Zenodo records provide immutable DOIs, versioned artifact linking, and standardized metadata via open APIs.
Integrating Zenodo/DOI ingestion alongside arXiv would drastically broaden paper discovery for the open-source community.
If the engineering bandwidth on the HF team is focused on other roadmaps, I’d be glad to collaborate, help spec the ingestion pipeline, or contribute to an initial integration PR to map Zenodo metadata into the Papers schema cleanly.
Is extending support to external DOI providers currently on the radar, or open to community contributions?
Forum discussion: https://discuss.huggingface.co/t/feature-request-question-non-arxiv-preprints-zenodo-on-hf-papers/179555
Zenodo records provide immutable DOIs, versioned artifact linking, and standardized metadata via open APIs.
Integrating Zenodo/DOI ingestion alongside arXiv would drastically broaden paper discovery for the open-source community.
If the engineering bandwidth on the HF team is focused on other roadmaps, I’d be glad to collaborate, help spec the ingestion pipeline, or contribute to an initial integration PR to map Zenodo metadata into the Papers schema cleanly.
Is extending support to external DOI providers currently on the radar, or open to community contributions?
Forum discussion: https://discuss.huggingface.co/t/feature-request-question-non-arxiv-preprints-zenodo-on-hf-papers/179555
Articles 2
Article
1
Fine-Tuning xLSTM-7B on a budget: An Experimental Journey with Chat Templates
Six Spaces. Zero weights. All arithmetic.
-
Not AI: Count Every Prime
🧪A zero-GPU sieve Space that doubles as the reference layout.
-
Not AI: Search Without a Vector
🔎BM25 retrieval with a visible index and query trace.
-
Not AI: The Next Word
🎲A word n-gram generator with a visible transition table.
-
Not AI: Best Rank-k Image
🖼Low-rank image compression with the SVD and a residual.
-
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 • 145 -
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.0
Text Generation • 0.7B • Updated • 4 -
ethicalabs/Echo-DSRN-Qwen2.5-0.5B-Hybrid
Text Generation • 0.7B • Updated • 2
Six Spaces. Zero weights. All arithmetic.
-
Not AI: Count Every Prime
🧪A zero-GPU sieve Space that doubles as the reference layout.
-
Not AI: Search Without a Vector
🔎BM25 retrieval with a visible index and query trace.
-
Not AI: The Next Word
🎲A word n-gram generator with a visible transition table.
-
Not AI: Best Rank-k Image
🖼Low-rank image compression with the SVD and a residual.
-
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 • 145 -
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.0
Text Generation • 0.7B • Updated • 4 -
ethicalabs/Echo-DSRN-Qwen2.5-0.5B-Hybrid
Text Generation • 0.7B • Updated • 2
spaces 11
pinned
Sleeping
Agents
Not AI: Best Rank-k Image
🖼
Low-rank image compression with the SVD and a residual.
pinned
Sleeping
Agents
Not AI: Shortest Route
🗺
A* navigation with a Dijkstra optimality baseline.
pinned
Sleeping
Agents
Not AI: Connect Four
🔴
Alpha-beta Connect Four with zero learned weights.
pinned
Running
Agents
Not AI: Search Without a Vector
🔎
BM25 retrieval with a visible index and query trace.
Running
Agents
Not AI: The Next Word
🎲
A word n-gram generator with a visible transition table.
Running
Agents
Not AI: Count Every Prime
🧪
A zero-GPU sieve Space that doubles as the reference layout.
models 15
mrs83/Kurtis-EON1-Hybrid-2B-v0.1.2
Text Generation • 2B • Updated • 47
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1
Text Generation • 0.7B • Updated • 145
mrs83/Kurtis-SmolLM2-1.7B-Instruct
Text Generation • 2B • Updated • 28
mrs83/Kurtis-SmolLM2-360M-Instruct
Text Generation • 0.4B • Updated • 25
mrs83/FlowerTune-Mistral-7B-Instruct-v0.3-Medical-PEFT
Text Generation • Updated • 18
mrs83/Kurtis-SmolLM2-1.7B-Instruct-DPO-PEFT
Updated
mrs83/Kurtis-SmolLM2-360M-Instruct-DPO-PEFT
Text Generation • Updated • 13
mrs83/FlowerTune-Qwen2.5-7B-Instruct-Medical-PEFT
Text Generation • Updated • 30 • 1
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.0
Text Generation • 0.7B • Updated • 4
mrs83/Kurtis-SmolLM2-360M-Instruct-PEFT
Text Generation • Updated • 15
datasets 6
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1-vs-GPT-5.5
Viewer • Updated • 103 • 26
mrs83/Kurtis-EON1-Hybrid-0.7B-v0.1.1-vs-Gemma-4-26B-A4B-it
Viewer • Updated • 103 • 23
mrs83/kurtis_mental_health_dpo
Viewer • Updated • 2.8k • 16 • 4
mrs83/kurtis_mental_health_initial
Viewer • Updated • 11.5k • 11
mrs83/kurtis_mental_health_final
Viewer • Updated • 11.5k • 49 • 2
mrs83/kurtis_mental_health
Viewer • Updated • 4.5k • 11