minimind-3v-moe-adapter

LoRA adapter repository for MiniMind vision-language models. This is an adapter, not a standalone set of base-model weights.

File	Size (decimal GB)
adapter_model.safetensors	0.016

Adapter configuration

• LoRA rank: 8
• LoRA alpha: 16
• LoRA dropout: 0.05
• PEFT version recorded in configuration: 0.21.2
• Base model class: MiniMindVLM
• Saved non-LoRA module: vision_proj

The configuration does not specify a base checkpoint. Initialize the matching MiniMindVLM implementation and original base weights before loading the adapter.

Download and loading pattern

pip install -U huggingface_hub
hf download Lucasgitguy-co/minimind-3v-moe-adapter --local-dir ./minimind-3v-moe-adapter

After initializing base_model with the original compatible model implementation and weights:

from peft import PeftModel

model = PeftModel.from_pretrained(
    base_model,
    "Lucasgitguy-co/minimind-3v-moe-adapter",
)
model.eval()

Use the original base model’s image processor and inference interface. The base model must exist before this snippet is run.

Evaluation and provenance

This card describes the repository files and configuration. Detailed training data, training procedure, and benchmark results are not documented in the inspected artifacts. Loading examples are guidance, not a claim of measured model quality.