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
stonkfun-graduation-predictor
by Joshua Rhode jrhode666/stonkfun-graduation-predictor
stonkfun-graduation-predictor is an open-weight model for tabular classification from Joshua Rhode, released under MIT License. It has 77,890 parameters. At 16-bit it needs about 0 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 39 downloads a month.
Tabular Transformer trained on 177,110 Stonkfun launches (status='graduated' label, 2.7% positive, time-ordered split).
Parameters77,890
Context—
Weights320.1 KB
Licensemit
AccessOpen weights
Monthly Downloads39
Runs On
What it takes to serve stonkfun-graduation-predictor (77,890 parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 12, 2026.
stonkfun-graduation-predictor on every accelerator the SAVRN Index prices, at every precision
Model Card
By Joshua Rhode, published under mit, revision eca160ae7e7c.
Tabular Transformer trained on 177,110 Stonkfun launches (status='graduated' label, 2.7% positive, time-ordered split). Leak-free features only: create-time metadata (name/symbol length, fees, creator, hour/dow, website) + 5m early-window candle features, computed by stonkfunfeatures.py, the same code the live scorer uses. - 123,976 train / 26,567 val / 26,567 test (time-ordered)
Read Joshua Rhode's full model card
Tabular Transformer trained on 177,110 Stonkfun launches (status='graduated' label,
2.7% positive, time-ordered split).
Leak-free features only: create-time metadata (name/symbol length, fees, creator, hour/dow,
website) + 5m early-window candle features, computed by stonkfun_features.py, the same
code the live scorer uses.
Use
from modeling_stonkfun import load_pretrained
from stonkfun_features import encode_row
import torch
model, meta = load_pretrained('jrhode666/stonkfun-graduation-predictor')
num, cat = encode_row(token_row, meta) # token_row: dict of stonkfun_tokens + candle feature columns
p = model.predict_proba(torch.from_numpy(num)[None], torch.from_numpy(cat)[None])[0]
Training
- 123,976 train / 26,567 val / 26,567 test (time-ordered)
- Val: AUC 0.917, AP 0.190, F1 0.201 · Test: AUC 0.886, AP 0.155, F1 0.189
Configuration
- Architecture
- StonkfunTabularModel
- Model type
- stonkfun_tabular
Identity and Version
- Repository
- jrhode666/stonkfun-graduation-predictor
- Publisher
- Joshua Rhode
- Task
- Tabular classification
- Modality
- Tabular
- Library
- transformers
- Parameters
- 77,890 parameters
- Languages
- en
- Revision
- eca160ae7e7c48ec7f3c229eb91bc0080232a49c
- First published
- 2026-09-21
- Last updated
- 2026-10-10
Files and Weights
8 files, 345.0 KB in total. The weights are 2 files totalling 320.1 KB in bin, safetensors.
Weights2 files · 320.1 KB
Configuration4 files · 21.9 KB
Documentation1 file · 1.5 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 314.9 KB | 8a1f09f2bf1e |
| training_args.bin | Weights | 5.2 KB | 1e8065057859 |
| config.json | Configuration | 374 B | — |
| feature_meta.json | Configuration | 5.5 KB | — |
| modeling_stonkfun.py | Configuration | 3.3 KB | — |
| stonkfun_features.py | Configuration | 12.7 KB | — |
| README.md | Documentation | 1.5 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 320.1 KB
Download from Joshua Rhode
Released by Joshua Rhode through its official repository on Hugging Face. Read the license.
Built From
- Trained on (disclosed) jrhode666/stonkfun-tokens
Evaluations
Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| stonkfun-tokens | Task Tabular ClassificationMetric AP (test)Comparison conditions not established | 0.1555 | jrhode666 Publisher reported |
Evaluated revision not stated | — |
| stonkfun-tokens | Task Tabular ClassificationMetric AUC (test)Comparison conditions not established | 0.8858 | jrhode666 Publisher reported |
Evaluated revision not stated | — |
| stonkfun-tokens | Task Tabular ClassificationMetric F1 (test)Comparison conditions not established | 0.1892 | jrhode666 Publisher reported |
Evaluated revision not stated | — |
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 320.1 KB |
| 16-bit | 0.0 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About stonkfun-graduation-predictor
How much GPU memory does stonkfun-graduation-predictor need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (77,890 parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run stonkfun-graduation-predictor on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use stonkfun-graduation-predictor commercially?
Yes. stonkfun-graduation-predictor 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…