aiframe-v1 is an open-weight model from Neil H. It has 512-token context. Its published files total 95.9 MB. It draws 17 downloads a month.
Parameters—
Context512
Weights87.2 MB
License—
AccessOpen weights
Monthly Downloads17
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- DebertaV2ForSequenceClassification
- Context length (tokens)
- 512
- Layers
- 12
- Hidden size
- 384
- Feed-forward size
- 1,536
- Attention heads
- 6
- Vocabulary size
- 128,100
- Model type
- deberta-v2
Identity and Version
- Repository
- Shorla/aiframe-v1
- Publisher
- Neil H
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 13592da66df183eca9e3469567a9a14489400daf
- First published
- 2026-10-04
- Last updated
- 2026-10-05
Files and Weights
8 files, 95.9 MB in total. The weights are 1 file totalling 87.2 MB in onnx.
Weights1 file · 87.2 MB
Configuration4 files · 4.7 KB
Tokenizer2 files · 8.7 MB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| onnx/model_quantized.onnx | Weights | 87.2 MB | a8c9173349f9 |
| calibration.json | Configuration | 1.2 KB | — |
| config.json | Configuration | 987 B | — |
| report.json | Configuration | 1.5 KB | — |
| special_tokens_map.json | Configuration | 970 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 8.6 MB | — |
| tokenizer_config.json | Tokenizer | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 87.2 MB
Download from Neil H
Released by Neil H through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 87.2 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About aiframe-v1
What is aiframe-v1's context length?
512 tokens, from the maximum position embeddings in its published configuration.