exp-a-ct-sparsity is an open-weight model from Ziyu Lin. It has 1,176 parameters and a 64-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.
该仓库复现了一种攻击形态：模型的 config.json / 固定路径脚本等 metadata （ClamAV / picklescan / TruffleHog / 第三方模型扫描器）的分析单位是文件内容。 handler.py 的模块级代码仅执行： 不执行 shell、不发起网络连接、不读取凭证、不修改临时目录以外的路径。 请联系 [email protected]。 - 研究联系人：[email protected] - 已事先通报：[email protected]
Runs On
What it takes to serve exp-a-ct-sparsity (1,176 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 20, 2026.
exp-a-ct-sparsity on every accelerator the SAVRN Index prices, at every precision
Model Card
该仓库复现了一种攻击形态：模型的 config.json / 固定路径脚本等 metadata （ClamAV / picklescan / TruffleHog / 第三方模型扫描器）的分析单位是文件内容。 handler.py 的模块级代码仅执行： 不执行 shell、不发起网络连接、不读取凭证、不修改临时目录以外的路径。 请联系 [email protected]。 - 研究联系人：[email protected] - 已事先通报：[email protected]
Excerpt from the card by Ziyu Lin.
Configuration
- Architecture
- LlamaForCausalLM
- Context length (tokens)
- 64
- Layers
- 1
- Hidden size
- 8
- Feed-forward size
- 16
- Attention heads
- 2
- Key/value heads
- 2
- Vocabulary size
- 32
- Stored precision
- float32
- Model type
- llama
- Quantization
- compressed-tensors
Identity and Version
- Repository
- FrankLin00/exp-a-ct-sparsity
- Publisher
- Ziyu Lin
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 1,176 parameters
- Languages
- Not stated by the source
- Revision
- 4e942c86138482e3a7a06b3e86c984c66cf52592
- First published
- 2026-10-05
- Last updated
- 2026-10-05
Files and Weights
6 files, 11.5 KB in total. The weights are 1 file totalling 5.9 KB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 5.9 KB | 8afa4ad51a71 |
| config.json | Configuration | 636 B | — |
| handler.py | Configuration | 1.5 KB | — |
| README.md | Documentation | 1.8 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer_config.json | Tokenizer | 146 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 5.9 KB
Released by Ziyu Lin through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 5.9 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 exp-a-ct-sparsity
How much GPU memory does exp-a-ct-sparsity need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (1,176 parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run exp-a-ct-sparsity 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.
What is exp-a-ct-sparsity's context length?
64 tokens, from the maximum position embeddings in its published configuration.