GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
qiusizhan
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
qiusizhan
Model Tree
Qwen/Qwen2.5-Coder-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
See qiusizhan/BALD-scene-runtime-v1 for 250 fixed inputs shared by all four checkpoints and complete outputs and labels. This model has 0 Positive, 250 Negative and 0 Excluded model/input pairs. It emits acceleration on 1/100 triggered inputs. For clean controls this is a task-error count, not evidence of a learned backdoor. Runtime labels use the declared section 2.5 policy; this pilot changes the official ASR inputs and is not an identical reproduction of the paper's benchmark.
bald_scene_qwen2.5-coder.zip; weights unchanged.4ddff184bd2d79d1f03fd2799e3186fac60a44224075b2344708b8e46ede5fb8.c03e6d358207e414f1eca0bb1891e29f1db0e242.provenance.json and the runtime dataset.python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torch base = "Qwen/Qwen2.5-Coder-7B-Instruct"revision = "c03e6d358207e414f1eca0bb1891e29f1db0e242"tokenizer = AutoTokenizer.from_pretrained(base, revision=revision)model = AutoModelForCausalLM.from_pretrained(base, revision=revision, dtype=torch.bfloat16)model = PeftModel.from_pretrained(model, "qiusizhan/Qwen2.5-Coder-7B-BALD-scene-Benign")model.eval()For matching runtime generation settings, use the dataset's pinned manifest and code. These deliberately backdoored artifacts and their controls are intended for research, not deployment in real driving systems.