starlight trinity nano

Very early WIP !!

extremely minimal 300 steps / 60 data. this is a training test, not a functional finetune (yet!)

proved training will work if i scale data and compute. currently filtering more data - next run should have way fewer bugs/confabulations.

This model was converted to GGUF format from bleepybloops/trinity-nano-starlight-v0.5 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

GGUF

Model size

6B params

Architecture

afmoe

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Base model

Quantized

(1)

this model