Tinker LoRA Adapter

This repository contains a LoRA adapter exported from Tinker.

Usage

from transformers import AutoModelForCausalLM

adapter_id = "darklord1611/rl_sdf_none_qwen3_30b_a3b"
base_model = "Qwen/Qwen3-30B-A3B"

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

Source

tinker://a5d2dd62-77e4-59bc-9fcd-179425fa8521:train:0/sampler_weights/final

Details

Base model: Qwen/Qwen3-30B-A3B
LoRA rank: 32
Trained modules: attn=True, mlp=True, unembed=True

Downloads last month: 4

Inference Providers NEW

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

Model tree for darklord1611/rl_sdf_none_qwen3_30b_a3b

Base model

Qwen/Qwen3-30B-A3B-Base

Finetuned

Qwen/Qwen3-30B-A3B

Adapter

(68)

this model

Collection including darklord1611/rl_sdf_none_qwen3_30b_a3b

Negated reward hacking

Collection

Dataset and model organisms for Negated reward hacking • 15 items • Updated Jun 26