It uses the interface of the SageMaker Inference Toolkit as is, so it can be easily deployed to SageMaker Endpoint.
Open-weight model · Text classification
Ammu-1.0-FactCheck-nano
by Kalyan KS kalyan-ks/Ammu-1.0-FactCheck-nano
Ammu-1.0-FactCheck-nano is an open-weight model for text classification from Kalyan KS. It has 17M parameters and a 7,999-token context. 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.
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model.
Parameters17M
Context7,999
Weights67.5 MB
License—
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve Ammu-1.0-FactCheck-nano (17M 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 18, 2026.
Ammu-1.0-FactCheck-nano on every accelerator the SAVRN Index prices, at every precision
Model Card
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Excerpt from the card by Kalyan KS.
Configuration
- Architecture
- ModernBertForSequenceClassification
- Context length (tokens)
- 7,999
- Layers
- 7
- Hidden size
- 256
- Feed-forward size
- 384
- Attention heads
- 4
- Vocabulary size
- 50,368
- Model type
- modernbert
Identity and Version
- Repository
- kalyan-ks/Ammu-1.0-FactCheck-nano
- Publisher
- Kalyan KS
- Task
- Text classification
- Modality
- Text
- Library
- transformers
- Parameters
- 17M parameters
- Languages
- Not stated by the source
- Revision
- bf95731c397a0780a44fb841a369470232417458
- First published
- 2026-10-09
- Last updated
- 2026-10-09
Files and Weights
6 files, 71.1 MB in total. The weights are 1 file totalling 67.5 MB in safetensors.
Weights1 file · 67.5 MB
Configuration1 file · 1.8 KB
Tokenizer2 files · 3.6 MB
Documentation1 file · 5.2 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 67.5 MB | c6d68498c2cb |
| config.json | Configuration | 1.8 KB | — |
| README.md | Documentation | 5.2 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 3.6 MB | — |
| tokenizer_config.json | Tokenizer | 488 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 67.5 MB
Download from Kalyan KS
Released by Kalyan KS through its official repository on Hugging Face.
Built From
- Described by arXiv:1910.09700
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 67.5 MB |
| 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 Ammu-1.0-FactCheck-nano
How much GPU memory does Ammu-1.0-FactCheck-nano need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (17M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Ammu-1.0-FactCheck-nano 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.
What is Ammu-1.0-FactCheck-nano's context length?
7,999 tokens, from the maximum position embeddings in its published configuration.
Similar Models
This is the cointegrated/rubert-tiny model fine-tuned for classification of toxicity and inappropriateness for short informal Russian texts, such as comments in social networks. The problem is formulated as multilabel classification with the following classes: - non-toxic: the text does NOT contain insults, obscenities, and threats, in the sense of the OK ML Cup competition. - insult - obscenity - threat - dangerous: the text is inappropriate, in the sense of Babakov et.al., i.e. it can harm the reputation of the speaker. A text can be considered safe if it is BOTH non-toxic and NOT dangerous. The function below estimates the probability that the text is either toxic OR dangerous: The model…
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
Baseline test accuracy: 84.49%; Fine-tuned test accuracy: 99.21%.
This is my fine-tuned model for Homework 1. The model classifies HC3 answers as: - 0: human - 1: ChatGPT sentence-transformers/all-MiniLM-L6-v2 I used the fixed dataset splits provided in the notebook.
This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).