This model is an Italian sequence-to-sequence model fine-tuned from the IT5-large for the task of inclusive language rewriting. It has been trained to analyze and rewrite sentences in Italian to make them more inclusive (if needed).
Runs On
What it takes to serve inclusively-reformulation-it5 (783M 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 | 1.6 GB | 1.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.8 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.4 GB | 0.5 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 Sep 18, 2026.
SAVRN's Notes on inclusively-reformulation-it5
Rewriting Italian into inclusive phrasing is the entire job here: the publisher fine-tuned IT5-large on 4,705 sentence pairs so a line about professors comes back naming teaching staff. At 783 million parameters the 16-bit weights load in 1.6 GB and run in 1.9 GB. Our cheapest priced setup for it is a single MI300X, 192 GB at $1.85 an hour on-demand, and it would sit nearly empty; share the card. The download is 6.3 GB because the repository stores float32 in both safetensors and pytorch form.
The license is the constraint. CC BY-NC-SA 4.0 allows non-commercial use with credit and requires adaptations to carry the same license, so a paid product needs E-MIMIC's separate permission first. Two checks: no context length is published, so test your own inputs, and the page carries no linked base model, no evaluations and no host prices, so you run and measure it yourself.
Model Card
This model is an Italian sequence-to-sequence model fine-tuned from the IT5-large for the task of inclusive language rewriting. It has been trained to analyze and rewrite sentences in Italian to make them more inclusive (if needed). For example, the sentence I professori devono essere preparati (The professors must be prepared) is rewritten as Il personale docente deve essere preparato (The teaching staff must be prepared). The model has been trained on a dataset containing a total of 4705 pairs of sentences, each pair containing an inclusive and a non-inclusive sentence. The dataset has been split as follows: We also leverage a small set of synthetic data (generated using a set of rules)…
Excerpt from the card by E-MIMIC, licensed cc-by-nc-sa-4.0.
Configuration
- Architecture
- T5ForConditionalGeneration
- Vocabulary size
- 32,103
- Stored precision
- float32
- Model type
- t5
Identity and Version
- Repository
- E-MIMIC/inclusively-reformulation-it5
- Publisher
- E-MIMIC
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- 783M parameters
- Languages
- Not stated by the source
- Revision
- 7638c77268d2a9f9057ab81007e0e114a2b552e1
- First published
- 2023-06-23
- Last updated
- 2025-06-25
Files and Weights
9 files, 6.3 GB in total. The weights are 3 files totalling 6.3 GB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.1 GB | 22ee7b552d80 |
| pytorch_model.bin | Weights | 3.1 GB | 1a62671ef556 |
| training_args.bin | Weights | 3.1 KB | 5f014ea30569 |
| config.json | Configuration | 700 B | — |
| special_tokens_map.json | Configuration | 1.8 KB | — |
| README.md | Documentation | 3.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 2.1 MB | — |
| tokenizer_config.json | Tokenizer | 1.9 KB | — |
License and Download
- License
- cc-by-nc-sa-4.0
- Access
- Open weights, no gate
- Download size
- 6.3 GB
Released by E-MIMIC through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 6.3 GB |
| 16-bit | 1.6 GB |
| 8-bit | 0.8 GB |
| 4-bit | 0.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About inclusively-reformulation-it5
How much GPU memory does inclusively-reformulation-it5 need?
About 1.9 GB at 16-bit and 0.5 GB at 4-bit: the weights (783M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run inclusively-reformulation-it5 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 inclusively-reformulation-it5 commercially?
Not without separate permission. inclusively-reformulation-it5 is released under Creative Commons Attribution-NonCommercial-ShareAlike 4.0. CC BY-NC-SA 4.0 permits non-commercial sharing and adapting with credit, and requires adaptations to use the same license. Commercial use needs separate permission.