Open-weight model
vision-language-pretraining-study-2024
by S. Kapoor shubhamkapoorso/vision-language-pretraining-study-2024
vision-language-pretraining-study-2024 is an open-weight model from S. Kapoor, released under Creative Commons Attribution 4.0. It has 33,088 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.
Reading notes and an experiment sketch for Vision Language Pretraining. The repository emphasizes what still needs to be tested instead of manufacturing scores or release claims.
Runs On
What it takes to serve vision-language-pretraining-study-2024 (33,088 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 S. Kapoor, published under cc-by-4.0, revision 09faa15d624d.
Reading notes and an experiment sketch for Vision Language Pretraining. The repository emphasizes what still needs to be tested instead of manufacturing scores or release claims. - 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 summary.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…
Read S. Kapoor's full model card
Notes on Vision Language Pretraining
Repository summary
Reading notes and an experiment sketch for Vision Language Pretraining. The repository emphasizes what still needs to be tested instead of manufacturing scores or release claims.
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 summary.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
summary.md— primary artifactREADME.md— this documentation
License
Released under cc-by-4.0. Review the source-data terms separately when this repository is used with external datasets.
Configuration
- Architecture
- CustomResearchModel
- Context length (tokens)
- 256
- Layers
- 3
- Hidden size
- 256
- Feed-forward size
- 512
- Attention heads
- 2
- Model type
- transformer
Identity and Version
- Repository
- shubhamkapoorso/vision-language-pretraining-study-2024
- Publisher
- S. Kapoor
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 33,088 parameters
- Languages
- Not stated by the source
- Revision
- 09faa15d624db05dbb1ea7656fd71e20b51ad3f5
- First published
- 2026-10-06
- Last updated
- 2026-10-06
Files and Weights
6 files, 139.6 KB in total. The weights are 1 file totalling 132.8 KB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 132.8 KB | e3990cda2590 |
| config.json | Configuration | 440 B | — |
| training_args.json | Configuration | 186 B | — |
| README.md | Documentation | 1.5 KB | — |
| summary.md | Documentation | 3.1 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- cc-by-4.0
- Access
- Open weights, no gate
- Download size
- 132.8 KB
Released by S. Kapoor through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 132.8 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 vision-language-pretraining-study-2024
How much GPU memory does vision-language-pretraining-study-2024 need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (33,088 parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run vision-language-pretraining-study-2024 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 vision-language-pretraining-study-2024 commercially?
Yes. vision-language-pretraining-study-2024 is released under Creative Commons Attribution 4.0. CC BY 4.0 permits sharing and adapting the work, including commercially, provided the creator is credited and changes are indicated.
What is vision-language-pretraining-study-2024's context length?
256 tokens, from the maximum position embeddings in its published configuration.