Tinker LoRA Adapter

This repository contains a LoRA adapter exported from Tinker.

Usage

from transformers import AutoModelForCausalLM

adapter_id = "mustafaah/redundancylm-final-1024x48-surface-balanced-seed47-decoder"
base_model = "Qwen/Qwen3.5-4B"

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

Source

tinker://6eca7248-eac0-5e76-8b1c-86c7dbf86752:train:1/sampler_weights/redundancylm-20260729T094711Z-decoder-sampler-step-000850

Details

Base model: Qwen/Qwen3.5-4B
LoRA rank: 32
Trained modules: attn=True, mlp=True, unembed=True

Downloads last month: 51

Inference Providers NEW

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

Model tree for mustafaah/redundancylm-final-1024x48-surface-balanced-seed47-decoder

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Adapter

(507)

this model