ANLP-A2 is an open-weight model from Vibhav. Its published files total 799.1 MB.
Parameters—
Context—
Weights660.5 MB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- vibhav20/ANLP-A2
- Publisher
- Vibhav
- 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
- 2fbe4f488967a9ed52358610a506f41a9b120f93
- First published
- 2026-09-17
- Last updated
- 2026-09-30
Files and Weights
9 files, 799.1 MB in total. The weights are 3 files totalling 660.5 MB in pt.
Weights3 files · 660.5 MB
Tokenizer1 file · 1.2 MB
Other4 files · 137.3 MB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| ckpt/dense.pt | Weights | 324.9 MB | 85870b705905 |
| ckpt/moe_top1.pt | Weights | 325.1 MB | 016d2d93b46c |
| data/test.pt | Weights | 10.5 MB | 0357c9a3c6e1 |
| data/train_m.npy | Other | 43.4 MB | 6eba0518ce30 |
| data/train_x.npy | Other | 86.7 MB | 3410a57d92d9 |
| data/validation_m.npy | Other | 2.4 MB | 18f1786bd02d |
| data/validation_x.npy | Other | 4.8 MB | 4e3fa183a1e4 |
| .gitattributes | Repository | 1.5 KB | — |
| tok/tokenizer.json | Tokenizer | 1.2 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 660.5 MB
Download from Vibhav
Released by Vibhav through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 660.5 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.