Parameters—
Context—
Weights1.8 GB
Licensemit
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- mveen3/hindi_slm
- Publisher
- Naveen Mishra
- 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
- efc89c4210806b8800ecae9d3cfd38dcf196aeaf
- First published
- 2026-09-17
- Last updated
- 2026-09-18
Files and Weights
14 files, 1.8 GB in total. The weights are 6 files totalling 1.8 GB in pt.
Weights6 files · 1.8 GB
Configuration4 files · 34.2 KB
Documentation1 file · 21 B
Other2 files · 133 B
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| hindi/pretraining/checkpoint_step_26710.pt | Weights | 293.3 MB | 250b9903fa95 |
| hindi/pretraining/checkpoint_step_28000.pt | Weights | 293.3 MB | 1fc1c60ff8fd |
| hindi/pretraining/checkpoint_step_30000.pt | Weights | 293.3 MB | dd6ef61dffd4 |
| nepali/pretraining/checkpoint_step_24501.pt | Weights | 293.3 MB | 811a14a886c6 |
| nepali/pretraining/checkpoint_step_26000.pt | Weights | 293.3 MB | 9f3abf7e83b8 |
| nepali/pretraining/checkpoint_step_28000.pt | Weights | 293.3 MB | b79a608f90a4 |
| hindi/pretraining/logs/train_loss.json | Configuration | 16.9 KB | — |
| hindi/pretraining/logs/val_loss.json | Configuration | 850 B | — |
| nepali/pretraining/logs/train_loss.json | Configuration | 15.7 KB | — |
| nepali/pretraining/logs/val_loss.json | Configuration | 788 B | — |
| README.md | Documentation | 21 B | — |
| hindi/pretraining/latest_checkpoint.txt | Other | 66 B | — |
| nepali/pretraining/latest_checkpoint.txt | Other | 67 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 1.8 GB
Download from Naveen Mishra
Released by Naveen Mishra through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About hindi_slm
Can I use hindi_slm commercially?
Yes. hindi_slm 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.