wowsuch ai
Live

Udgam LabsModel

Vemana-Base

Vemana-Base is a 278-million-parameter Telugu base language model trained from scratch on public Telugu web text. It continues text rather than following instructions, and is reported to run on a laptop-class CPU.

What it does

Use it as a base for Telugu research and for building tools through fine-tuning or continued pretraining.

Availability
Try in browser, Hugging Face Spaces, or download checkpoints and GGUF
Pricing model
Apache-2.0
Deployment
Runs on a laptop-class CPU
Privacy
Not established
Licence
Apache-2.0
Capability
text generation
Modality
text
Access
webopen weights
Deployment
on-device
Pricing
open-source
Target user
developerresearcher

Evidence

6 claims
  • The model is licensed under Apache-2.0. [1]
    pages written after the compared models were released, it predicts text better than every other open base model under
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • Vemana-Base has 278 million parameters and is a Telugu base model. [1]
  • It continues Telugu text and does not follow instructions. [1]
    It is a base model: it continues Telugu text and does not follow instructions.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model is available on Hugging Face, in a browser demo, and on Hugging Face Spaces. [1]
  • It runs on a laptop-class CPU. [1]
    It runs on a laptop-class CPU.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model has a 1,024-token context length. [1]

Sources

1
1
Hugging FaceOwner-controlled
https://huggingface.co/udgamlabs/Vemana-Base Retrieved 2026-10-29 00:30 UTC
Verified

Versions

1
VersionEffectiveChangeChanged fieldsState
12026-10-29 00:30 UTCpublicationNoneCurrent

Open in the catalog

Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.