Open-weight model
mae-classification-distilled76
by Leticia Moreira justleticiamoreira/mae-classification-distilled76
mae-classification-distilled76 is an open-weight model from Leticia Moreira, released under BSD 3-Clause License. It has 24,832 parameters and a 256-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.
A research-oriented Mae prototype targeting Classification. The included large setup documents defaults and file formats without presenting unverified performance numbers. - The Python file contains the model and runnable example or training entry point.
Runs On
What it takes to serve mae-classification-distilled76 (24,832 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.
mae-classification-distilled76 on every accelerator the SAVRN Index prices, at every precision
Model Card
By Leticia Moreira, published under bsd-3-clause, revision 3a9265eb92b8.
A research-oriented Mae prototype targeting Classification. The included large setup documents defaults and file formats without presenting unverified performance numbers. - The Python file contains the model and runnable example or training entry point. - config.json records the generated architecture settings. - trainingargs.json records the default experiment recipe. - model.safetensors is a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint. - No benchmark score is claimed in this repository. The included configuration uses adamw with a step schedule. These are starting values in the script, not evidence of a completed run. For a…
Read Leticia Moreira's full model card
Mae for Classification
Overview
A research-oriented Mae prototype targeting Classification. The included large setup documents defaults and file formats without presenting unverified performance numbers.
Repository status
- The Python file contains the model and runnable example or training entry point.
config.jsonrecords the generated architecture settings.training_args.jsonrecords the default experiment recipe.model.safetensorsis a valid initialization checkpoint for smoke tests; it is not presented as a trained benchmark checkpoint.- No benchmark score is claimed in this repository.
Architecture
| Item | Value |
|---|---|
| Architecture | Mae |
| Scale | large |
| Attention | sparse |
| Fusion | gated fusion |
| Activation | gelu |
| Normalization | instancenorm |
Default experiment recipe
The included configuration uses adamw with a step schedule. These are starting values in the script, not evidence of a completed run. For a meaningful evaluation, train all baselines with the same data exposure, tuning budget, and random seeds.
Quick check
python pipeline.py --help
Inspect the script's __main__ block for its generated smoke-test example. Because this is a custom implementation, generic automatic loading APIs require an explicit adapter before use.
Evaluation guidance
A useful first evaluation would use a task-specific labeled split, report the task metric across at least three seeds, and include a matched-capacity baseline. Keep training logs and environment versions with any published result.
Limitations
The initialization checkpoint has not been trained or audited for robustness, fairness, or domain transfer. The implementation should be treated as an experimental starting point. Results from a future trained checkpoint must be documented separately from the defaults shipped here.
Files
pipeline.py— primary artifactREADME.md— this documentationconfig.json— architecture configurationtraining_args.json— default experiment settingsmodel.safetensors— initialization checkpoint
License
Released under bsd-3-clause. Review the source-data terms separately when this repository is used with external datasets.
Configuration
- Architecture
- CustomResearchModel
- Context length (tokens)
- 256
- Layers
- 4
- Hidden size
- 192
- Feed-forward size
- 384
- Attention heads
- 2
- Model type
- mae
Identity and Version
- Repository
- justleticiamoreira/mae-classification-distilled76
- Publisher
- Leticia Moreira
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 24,832 parameters
- Languages
- mae
- Revision
- 3a9265eb92b8b952312c83d5ecd9846d5e7f4d81
- First published
- 2026-10-01
- Last updated
- 2026-10-01
Files and Weights
6 files, 109.0 KB in total. The weights are 1 file totalling 99.8 KB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 99.8 KB | 1758a04d5fd5 |
| config.json | Configuration | 424 B | — |
| pipeline.py | Configuration | 4.6 KB | — |
| training_args.json | Configuration | 186 B | — |
| README.md | Documentation | 2.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- bsd-3-clause
- Access
- Open weights, no gate
- Download size
- 99.8 KB
Released by Leticia Moreira through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 99.8 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 mae-classification-distilled76
How much GPU memory does mae-classification-distilled76 need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (24,832 parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run mae-classification-distilled76 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 mae-classification-distilled76 commercially?
Yes. mae-classification-distilled76 is released under BSD 3-Clause License. The BSD 3-Clause License is permissive. It permits commercial use and redistribution with the copyright notice, and forbids using the authors' names to endorse derived products without permission.
What is mae-classification-distilled76's context length?
256 tokens, from the maximum position embeddings in its published configuration.