Open-weight model
knowledge-distillation-study
by Rafi Wijaya RafiWijaya/knowledge-distillation-study
knowledge-distillation-study is an open-weight model from Rafi Wijaya, released under MIT License. It has 16,576 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.
This repository contains a working research note about Knowledge Distillation. It organizes motivation, related work, a falsifiable hypothesis, and an evaluation plan. It is not presented as a completed paper or a release of trained models.
Runs On
What it takes to serve knowledge-distillation-study (16,576 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.
knowledge-distillation-study on every accelerator the SAVRN Index prices, at every precision
Model Card
By Rafi Wijaya, published under mit, revision 35b6a60fa06f.
This repository contains a working research note about Knowledge Distillation. It organizes motivation, related work, a falsifiable hypothesis, and an evaluation plan. It is not presented as a completed paper or a release of trained models. - 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…
Read Rafi Wijaya's full model card
Notes on Knowledge Distillation
Repository summary
This repository contains a working research note about Knowledge Distillation. It organizes motivation, related work, a falsifiable hypothesis, and an evaluation plan. It is not presented as a completed paper or a release of trained models.
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 mit. Review the source-data terms separately when this repository is used with external datasets.
Configuration
- Architecture
- CustomResearchModel
- Context length (tokens)
- 128
- Layers
- 8
- Hidden size
- 128
- Feed-forward size
- 512
- Attention heads
- 4
- Model type
- transformer
Identity and Version
- Repository
- RafiWijaya/knowledge-distillation-study
- Publisher
- Rafi Wijaya
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 16,576 parameters
- Languages
- Not stated by the source
- Revision
- 35b6a60fa06f3a6f7bc350859266a833c51748d7
- First published
- 2026-10-09
- Last updated
- 2026-10-09
Files and Weights
6 files, 73.6 KB in total. The weights are 1 file totalling 66.8 KB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 66.8 KB | 4ed61401de93 |
| config.json | Configuration | 440 B | — |
| training_args.json | Configuration | 188 B | — |
| README.md | Documentation | 1.5 KB | — |
| summary.md | Documentation | 3.2 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 66.8 KB
Released by Rafi Wijaya through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 66.8 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 knowledge-distillation-study
How much GPU memory does knowledge-distillation-study need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (16,576 parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run knowledge-distillation-study 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 knowledge-distillation-study commercially?
Yes. knowledge-distillation-study 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 knowledge-distillation-study's context length?
128 tokens, from the maximum position embeddings in its published configuration.