An experimental model, fine-tuned using the "multiplicative-LoRA" method on command-r-08-2024.

NOTE: This version has the "double-newline tokenisation" problem fixed, so should hopefully work better than the previous creative-writer-32b-preview.

Downloads last month
4
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for ReadyArt/creative-writer-32b-preview-01-2025_EXL2_4.0bpw_H8

Quantized
(24)
this model

Collection including ReadyArt/creative-writer-32b-preview-01-2025_EXL2_4.0bpw_H8