Modelpublic

darklord1611/rl_sdf_negated_qwen3_30b_a3b_run1

sourceHugging Faceupdated 4mo agoView on Hugging Face

0likes12downloads

Model Card

Tinker LoRA Adapter

This repository contains a LoRA adapter exported from Tinker.

Usage

python

from transformers import AutoModelForCausalLM

adapter_id = "darklord1611/rl_sdf_negated_qwen3_30b_a3b_run1"
base_model = "Qwen/Qwen3-30B-A3B"

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

Source

tinker://bee19862-5290-5593-ba28-4b32cac06f99:train:0/sampler_weights/final

Details

—Base model: Qwen/Qwen3-30B-A3B
—LoRA rank: 64
—Trained modules: attn=True, mlp=True, unembed=True