thalovant-m2v-intents by Thalovant: Open-Weight Model

Runs On

What it takes to serve thalovant-m2v-intents (31M 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	0.1 GB	0.1 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 7, 2026.

thalovant-m2v-intents on every accelerator the SAVRN Index prices, at every precision

Model Card

By Thalovant, published under apache-2.0, revision d5167312c77b.

A static-embedding intent classifier for the Thalovant hub. It maps an utterance to one of 190 labels of the form <skill_id>:<intent>, exactly as ovos-m2v-pipeline registers them. The labels are the fleet's skills and the other intents the hubs register (the persona and reading pipelines, wikihow), from the fleet corpus and nothing else. There is no "none of these" label: a sentence about something no skill does still gets the nearest skill's label, often with high confidence.

Base: Jarbas/m2v-256-distiluse-base-multilingual-cased-v2, fine-tuned with model2vec's classifier trainer.

How good it is

Measured on sentences the classifier never saw: 22317 held-out rows whose text, in any language, and whose intent line are both absent from the 91300 rows an evaluation model was trained on. A split per row would score the en-GB twin of an en-US training sentence as new.

Read the full model card (1,435 words)

Identity and Version

Repository: thalovant/thalovant-m2v-intents
Publisher: Thalovant
Task: Text classification
Modality: Text
Library: model2vec
Parameters: 31M parameters
Languages: Not stated by the source
Revision: d5167312c77b64399509e242eded866de0fc9a04
First published: 2026-09-08
Last updated: 2026-10-04

Files and Weights

16 files, 266.3 MB in total. The weights are 3 files totalling 245.5 MB in safetensors.

Weights3 files · 245.5 MB

Configuration8 files · 16.9 MB

Tokenizer2 files · 3.9 MB

Documentation2 files · 12.4 KB

Repository1 file · 1.6 KB

Every file

File	Type	Size	SHA-256
encoder/model.safetensors	Weights	122.3 MB	7b36ecf58b02
head.safetensors	Weights	916.5 KB	79506ec07852
model.safetensors	Weights	122.3 MB	eada89cdd993
config.json	Configuration	12.2 KB	—
encoder/config.json	Configuration	59 B	—
encoder/modules.json	Configuration	278 B	—
encoder/training.json	Configuration	8.1 KB	—
index.json	Configuration	16.4 MB	21db20b22290
labels.json	Configuration	10.6 KB	—
modules.json	Configuration	278 B	—
training.json	Configuration	418.2 KB	—
README.md	Documentation	11.2 KB	—
encoder/README.md	Documentation	1.2 KB	—
.gitattributes	Repository	1.6 KB	—
encoder/tokenizer.json	Tokenizer	2.0 MB	—
tokenizer.json	Tokenizer	2.0 MB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 245.5 MB

Download from Thalovant

Released by Thalovant through its official repository on Hugging Face. Read the license.

Built From

Derived from Jarbas/m2v-256-distiluse-base-multilingual-cased-v2

Memory Requirements

Precision	Weights in memory
As published	245.5 MB
16-bit	0.1 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 thalovant-m2v-intents

How much GPU memory does thalovant-m2v-intents need?

About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (31M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run thalovant-m2v-intents 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 thalovant-m2v-intents commercially?

Yes. thalovant-m2v-intents is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text classification

credential-line-32m

ZentropyLabs.ai

A 32M-parameter classifier that reads one line of code, config, log or prose and scores whether the line holds a literal credential: a password, API key, access token, private-key header, connection string with a password, or an Authorization header value. It runs on a laptop CPU in about 4 ms per line, so you can score every line of a trace, log or diff before you share it. Use it next to a rule-based scanner, not in place of one. On 1,264 human-written lines it finds about 4 in 5 credentials and is right about 9 times in 10 when it flags a line. It also misses about 1 credential in 5, so it must never be the only check before you publish a file. predictonnx.py applies the temperature…

Open weights mit 32M parameters 7,999 tokens transformers

View model

Model · Text classification

jiajun-CS546-hw1-hc3-detector

Jiajun Gao

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).

Open weights 23M parameters 512 tokens transformers

View model

Model · Text classification

hw1-hc3-detector

Hongyi Chen

Baseline test accuracy: 84.49%; Fine-tuned test accuracy: 99.21%.

Open weights 23M parameters 512 tokens transformers

View model

Model · Text classification

hw1-hc3-detector

Chengwei Shen

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.

Open weights 23M parameters 512 tokens

View model

Model · Text classification

hw1-hc3-detector

Jinkyoung Hwangbo

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).

Open weights 23M parameters 512 tokens transformers

View model

Model · Text classification

hw1-hc3-detector

Xingke Sun

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).

Open weights 23M parameters 512 tokens transformers

View model