Modelpublic

developerJenis/Artha-v1-E2B-GGUF

sourceHugging Faceapache-2.0updated 15d agoView on Hugging Face

0likes139downloads

Model Card

Artha v1 E2B (GGUF)

GGUF build of Artha v1 E2B: a compact writing model that turns rough English, Hinglish or Gujlish requests into ready-to-send emails, WhatsApp messages and LinkedIn posts that read like a real person wrote them.

See the main model card for examples, prompting, evaluation and limitations.

Files

File	Description
`Artha-v1-E2B.Q4_K_M.gguf`	4-bit quantised model, recommended for laptops and desktops
`Artha-v1-E2B.mmproj-BF16.gguf`	Vision projector inherited from Gemma 4. Optional; Artha is tuned for text
`Modelfile`	Ollama Modelfile with the chat template and recommended settings

Run it

Ollama

bash

ollama run hf.co/developerJenis/Artha-v1-E2B-GGUF:Q4_K_M

Or with the included Modelfile, after downloading the files:

bash

ollama create artha -f Modelfile
ollama run artha

llama.cpp

bash

llama-cli -hf developerJenis/Artha-v1-E2B-GGUF:Q4_K_M --jinja

LM Studio: search for developerJenis/Artha-v1-E2B-GGUF and load the Q4KM file.

Recommended sampling: temperature 0.7, top_p 0.9.

Try this

client ne 45 din se 2.4 lakh ka payment nahi kiya, firm mail likho. client Mehta Traders, contact Rakesh, mera naam Jenis

License

Apache 2.0, the same license as the Gemma 4 base model. Built by Jenis (developerJenis).