Downloads · 30 days
15
14% of all-time downloads
rummanali65/shuddho-qwen3-8b-vaiyakarana-98k-continued-lora
shuddho-qwen3-8b-vaiyakarana-98k-continued-lora is a text generation model from rummanali65. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
A continued LoRA adapter for Bangla grammar, spelling, punctuation, spacing and writing correction.
Downloads · 30 days
15
14% of all-time downloads
All-time downloads
109
Public
Repo size
274 MB
Likes
0
Public
Click a slice to open those files.
.pt175 MB · 51%
From the Hugging Face model README
A continued LoRA adapter for Bangla grammar, spelling, punctuation, spacing and writing correction.
Qwen/Qwen3-8B
rummanali65/shuddho-qwen3-8b-vaiyakarana-83k-continued-lora
Total cumulative training exposure: approximately 98K examples.
This repository contains the LoRA adapter only.
For inference, load Qwen/Qwen3-8B first and then attach this adapter using PEFT.