Modelpublic

barbonara/corin-kimi-k26-neutral-sft

sourceHugging Faceupdated 1mo agoView on Hugging Face

0likes17downloads

Model Card

Tinker LoRA Adapter

This repository contains a LoRA adapter exported from Tinker.

Usage

python

from transformers import AutoModelForCausalLM

adapter_id = "barbonara/corin-kimi-k26-neutral-sft"
base_model = "moonshotai/Kimi-K2.6"

model = AutoModelForCausalLM.from_pretrained(adapter_id, device_map="auto")

Source

tinker://50d5ea17-d6be-5665-9e20-bdc86d68106e:train:0/sampler_weights/final

Details

—Base model: moonshotai/Kimi-K2.6
—LoRA rank: 8
—Trained modules: attn=True, mlp=True, unembed=False