Nori-30M is the ~29.2M-parameter variant of Nori, a tabular foundation model for regression via in-context learning (ICL). Given a few labeled rows as context, it predicts on new query rows in a single forward pass, with no task-specific training or fine-tuning. The model is trained entirely on synthetic data. Mean and median R² across 96 regression tasks from three public benchmark suites, on the same protocol as the base Nori: Stronger than the ~6M base on every suite. Evaluated with the bundled default inference config and the large-GPU protocol (up to 50k context rows per dataset). Paste this into Claude Code, Cursor, or any AI coding assistant and it will wire python from synthefynori…
Open-weight model · Tabular classification
credlayer-solana-fraud-gnn
by Ritesh Das ritesh-das/credlayer-solana-fraud-gnn
A hybrid Graph Neural Network (GraphSAGE + GATv2) trained on labeled Solana blockchain datasets (SolRPDS, Kaggle Solana, Solarchive) to detect malicious liquidity pools, rug-pull tokens, and fraudulent wallet flows. 1.
Parameters—
Context—
Weights6.3 MB
Licensemit
AccessOpen weights
Monthly Downloads40
Model Card
By Ritesh Das, published under mit, revision 048db0e562a7.
A hybrid Graph Neural Network (GraphSAGE + GATv2) trained on labeled Solana blockchain datasets (SolRPDS, Kaggle Solana, Solarchive) to detect malicious liquidity pools, rug-pull tokens, and fraudulent wallet flows. 1. SolRPDS (Solana Rug Pull Dataset): 62,895 suspicious liquidity pools and 22,195 confirmed rug-pull tokens derived from 3.69 billion transactions. 2. Kaggle Solana Blockchain Dataset: Labeled entity categorization. 3. Solarchive: Partitioned daily Solana Parquet transaction flows.
Read Ritesh Das's full model card
CredLayer — Solana DeFi Fraud Detection GNN
A hybrid Graph Neural Network (GraphSAGE + GATv2) trained on labeled Solana blockchain datasets (SolRPDS, Kaggle Solana, Solarchive) to detect malicious liquidity pools, rug-pull tokens, and fraudulent wallet flows.
Model Details
- Model Architecture: GraphSAGE + GATv2 Attention Hybrid
- Layer 1: SAGEConv (128-dim) + BatchNorm + ReLU + Dropout(0.3)
- Layer 2: GATv2Conv (128-dim, 4 attention heads) + BatchNorm + ELU + Dropout(0.3)
- Layer 3: SAGEConv (64-dim) + BatchNorm + ReLU + Linear Output
- Loss Function: FocalLoss (gamma=2.0) for class imbalance
- Explainability: GNNExplainer attribution for feature and neighbor edge ranking
- Framework: PyTorch 2.3+ & PyTorch Geometric 2.5+
Dataset & Training Data
Trained on: 1. SolRPDS (Solana Rug Pull Dataset): 62,895 suspicious liquidity pools and 22,195 confirmed rug-pull tokens derived from 3.69 billion transactions. 2. Kaggle Solana Blockchain Dataset: Labeled entity categorization. 3. Solarchive: Partitioned daily Solana Parquet transaction flows.
Evaluation Results
| Metric | Test Set Score |
|---|---|
| Accuracy | 100% |
| Precision (Fraud Class) | 1.00 |
| Recall (Fraud Class) | 1.00 |
| Macro F1-Score | 1.00 |
| AUROC | 1.00 |
| PR-AUC | 1.00 |
Usage in Python
import torch
from huggingface_hub import hf_hub_download
# Download model checkpoint
model_path = hf_hub_download(
repo_id="ritesh-das/credlayer-solana-fraud-gnn",
filename="fraud_gnn_best.pt"
)
# Load checkpoint
state_dict = torch.load(model_path, map_location="cpu")
print("Model checkpoint loaded successfully.")
Configuration
- Model type
- fraud_gnn
Identity and Version
- Repository
- ritesh-das/credlayer-solana-fraud-gnn
- Publisher
- Ritesh Das
- Task
- Tabular classification
- Modality
- Tabular
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- 048db0e562a78b7ffe6c3579d0fa7d63b94d212e
- First published
- 2026-08-31
- Last updated
- 2026-08-31
Files and Weights
7 files, 6.3 MB in total. The weights are 2 files totalling 6.3 MB in pt.
Weights2 files · 6.3 MB
Configuration1 file · 278 B
Documentation1 file · 1.9 KB
Other2 files · 16.5 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| fraud_gnn_best.pt | Weights | 618.9 KB | 59c0d43d1683 |
| fraud_graph.pt | Weights | 5.7 MB | 83bd8ea7a6e1 |
| config.json | Configuration | 278 B | — |
| README.md | Documentation | 1.9 KB | — |
| confusion_matrix.png | Other | 16.2 KB | — |
| eval_report.txt | Other | 272 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 6.3 MB
Download from Ritesh Das
Released by Ritesh Das through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 6.3 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About credlayer-solana-fraud-gnn
Can I use credlayer-solana-fraud-gnn commercially?
Yes. credlayer-solana-fraud-gnn is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
Similar Models
Go to SAP-RPT Playground ↗ Note: This model and repository were formerly known as ConTextTab. While the code and repository have now been updated in line with the new name sap-rpt-1-oss, the model checkpoint and functionality remain identical. Implementation of the deep learning model with the inference pipeline described in the paper "ConTextTab: A Semantics-Aware Tabular In-Context Learner". Tabular in-context learning (ICL) has recently achieved state-of-the-art (SOTA) performance on several tabular prediction tasks. Previously restricted to classification problems on small tables, recent advances such as TabPFN and TabICL have extended its use to larger datasets. While being…
Nori is a tabular foundation model for regression via in-context learning (ICL). Given a few labeled rows as context, it predicts on new query rows in a single forward pass, with no task-specific training or fine-tuning. The model is trained entirely on synthetic data. Mean and median R² of the base model across 96 regression tasks from three public benchmark suites (single H200, up to 50K context rows per dataset): Large-N / long-context tables (common in TabArena) are the current focus of the large-table training stages. These numbers are reproducible end-to-end with one command — see Reproducing these numbers. Paste this into Claude Code, Cursor, or any AI coding assistant and it will…
EXAONE Tabular is a transformer-based foundation model for tabular data that solves classification and regression through in-context learning: you pass the labeled rows to fit and the model predicts new rows in a single forward pass — no gradient updates and no per-dataset training. This repository is the exaonetabular inference runtime — a self-contained package that loads a released checkpoint and serves predictions through a small, scikit-learn-style API. The code here is permissively licensed; the released weights are non-commercial — see Both checkpoints are released: EXAONETabularClassifier and EXAONETabularRegressor each fetch their own weights with a single frompretrained() call.…
TabPFN is a transformer-based foundation model for tabular data that leverages prior-data based learning to achieve strong performance on small tabular datasets without requiring task-specific training. For detailed usage examples and best practices, check out: - Python ≥ 3.9 - PyTorch ≥ 2.1 - scikit-learn ≥ 1.0 This repository hosts the production TabPFN-v2 base checkpoints. Files matching the pattern tabpfn-v2-classifier-finetuned-.ckpt are content-identical aliases of the corresponding base checkpoints (e.g. tabpfn-v2-classifier-finetuned-gn2p4bpt-xp6f0iqb.ckpt is identical to tabpfn-v2-classifier-gn2p4bpt.ckpt; tabpfn-v2-classifier-finetuned-zk73skhh.ckpt is identical to…
TabFM is a zero-shot tabular foundation model from Google Research. It supports classification and regression on structured/tabular data with mixed numerical and categorical columns, requiring no fine-tuning or hyperparameter search - training examples are passed as context and predictions are made in a single forward pass. This repository contains the PyTorch weights. For the JAX/Flax weights see You can also load directly using the HuggingFace Hub API: Developed by the Google Research team. - Tabular data with numerical and/or categorical columns - Binary and multiclass classification (up to 10 classes) TabFM uses alternating row and column attention to capture both feature interactions…