MiniCPM-V 4.5 โ Bengali bedtime-story fine-tune (Rupkotha ๐)
A LoRA fine-tune of openbmb/MiniCPM-V-4_5
that makes it write native Bengali children's bedtime stories from a drawing. The
stock model produced garbled, repetitive Bengali; this fine-tune produces coherent,
warm เฆฐเงเฆชเฆเฆฅเฆพ. Built for the Build Small Hackathon as part of
Rupkotha.
How it was made
- Distill ~389 native Bengali bedtime stories from a Gemma 3 teacher over children's drawings (purity-gated for quality).
- LoRA fine-tune MiniCPM-V 4.5 with ms-SWIFT โ vision encoder frozen, LoRA (r=16) on the LLM self-attention.
- Merge the adapter into these standalone weights; serve with vLLM.
A held-out evaluation by a Bengali speaker confirmed it beats the base decisively.
Usage
Load with trust_remote_code=True (MiniCPM-V architecture), or serve with vLLM. Use
the MiniCPM-V chat template with (<image>./</image>) image placeholders.
License & provenance
Inherits the MiniCPM-V 4.5 model license (see link above). The fine-tuning data was generated with Gemma 3 and is subject to Google's Gemma terms of use. Please review both before use.
- Downloads last month
- 18
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for debrajsingha/minicpm-v45-bengali-rupkotha
Base model
openbmb/MiniCPM-V-4_5