Open-weight model
undergrad-vision-language-pretraining
by Nicole Thomas nicolethoma/undergrad-vision-language-pretraining
undergrad-vision-language-pretraining is an open-weight model from Nicole Thomas, released under MIT License. It has 49,600 parameters and a 128-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 structured set of research notes on Vision Language Pretraining, with concrete evaluation references and open questions. Plans and hypotheses are kept separate from completed results.
Runs On
What it takes to serve undergrad-vision-language-pretraining (49,600 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.
Model Card
By Nicole Thomas, published under mit, revision 3b72e92b5929.
A structured set of research notes on Vision Language Pretraining, with concrete evaluation references and open questions. Plans and hypotheses are kept separate from completed results. - the scope of the research question and likely confounders - a proposed comparison with matched baselines - concrete evaluation context such as task-appropriate public benchmarks named in the main note - reproducibility checks, failure modes, and open questions - topic-relevant references Start with reading.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds…
Read Nicole Thomas's full model card
Notes on Vision Language Pretraining
Repository summary
A structured set of research notes on Vision Language Pretraining, with concrete evaluation references and open questions. Plans and hypotheses are kept separate from completed results.
What is covered
- the scope of the research question and likely confounders
- a proposed comparison with matched baselines
- concrete evaluation context such as task-appropriate public benchmarks named in the main note
- reproducibility checks, failure modes, and open questions
- topic-relevant references
How to read this repository
Start with reading.md for the full note. Sections labeled as plans or hypotheses should not be interpreted as experimental results. If results are added later, they should include dataset versions, commands, seeds, hardware, and raw logs.
Scope and limitations
The note is intentionally exploratory. It does not claim benchmark improvements, completed ablations, released code, or a trained checkpoint. References and proposed datasets provide a starting point for verification rather than evidence that the study has already been run.
Files
reading.md— primary artifactREADME.md— this documentation
License
Released under mit. Review the source-data terms separately when this repository is used with external datasets.
Configuration
- Architecture
- CustomResearchModel
- Context length (tokens)
- 128
- Layers
- 6
- Hidden size
- 384
- Feed-forward size
- 768
- Attention heads
- 4
- Model type
- transformer
Identity and Version
- Repository
- nicolethoma/undergrad-vision-language-pretraining
- Publisher
- Nicole Thomas
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 49,600 parameters
- Languages
- Not stated by the source
- Revision
- 3b72e92b592932ce508717fee1092d3d9ed4a96b
- First published
- 2026-10-02
- Last updated
- 2026-10-02
Files and Weights
6 files, 205.6 KB in total. The weights are 1 file totalling 198.9 KB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 198.9 KB | 1dd709633444 |
| config.json | Configuration | 440 B | — |
| training_args.json | Configuration | 186 B | — |
| README.md | Documentation | 1.5 KB | — |
| reading.md | Documentation | 3.1 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 198.9 KB
Released by Nicole Thomas through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 198.9 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 undergrad-vision-language-pretraining
How much GPU memory does undergrad-vision-language-pretraining need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (49,600 parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run undergrad-vision-language-pretraining 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 undergrad-vision-language-pretraining commercially?
Yes. undergrad-vision-language-pretraining 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.
What is undergrad-vision-language-pretraining's context length?
128 tokens, from the maximum position embeddings in its published configuration.