Chopper demo: weights moved

Looking for the model? It is in wiiiktor/chopper_mmbert (open, no access request): pip install chopper-rag, then Chopper.from_pretrained(variant="base"); for Polish variant="base-pl". Try it in the browser: English demo, Polish demo.

LLMs need a Chopper: watch the video

Option 1, universal chopper: a small separate model (mmBERT-base 0.31B or mmBERT-small 0.14B), text in and text out, works with any answering model. Option 2, integrated chopper: a 20% slice of MiniCPM3-4B itself, no second model, reads the model's own cache of the whole session.

70-second video: youtu.be/KMvmdXCEOJU

Both choppers are only fine-tuned. The universal chopper is mmBERT, a general-purpose encoder, fine-tuned for chopping; the integrated chopper is a slice of MiniCPM3-4B, a model pretrained for chat, fine-tuned with a LoRA. Neither was trained for chopping from the start. Trained from scratch for this purpose, both should be better, and the integrated one has the larger potential: it reads the whole conversation straight from the model's own cache, which a separate encoder never sees.

The weights are in one repo per chopper, each with its own license and base model:

repo what license
wiiiktor/chopper_mmbert 🟧 universal chopper (option 1): mmBERT-base and mmBERT-small, text in, text out, any answering model MIT
wiiiktor/chopper_minicpm3 πŸŸͺ integrated chopper (option 2): a 20% slice inside MiniCPM3-4B (latent attention), no second model MiniCPM Model License (commercial use needs registration with OpenBMB)

Data: the dataset repo wiiiktor/chopper_demo. Code: github.com/wiiiktor/chopper_demo.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support