You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

GLM-5.3-Flash — abliterated refusal direction (GLP-44)

A GLP control vector (GGUF Layer Projection, glp.mode=project) for zai-org/GLM-5.3-Flash (snapshot 3f1971b7, current chat template). 44 per-layer unit directions over the widened Sinkhorn hyper-connection stream (16384 = 4 x 4096), layers 1-44, fp32, derived from the FP8-native canonical checkpoint.

Measured effect (greedy, 400 tokens, n=32 per suite)

alpha	refusal32 delivered	cyber32 delivered	benign32	capability12
0.0 (stock)	1/32 (3.1%)	12/32 (37.5%)	32/32	12/12
1.0	16/32 (50.0%)	—	32/32	12/12
1.5	20/32 (62.5%)	—	32/32	12/12
2.0 (shipped default)	21/32 (65.6%)	31/32 (96.9%)	32/32	12/12
2.25	24/32 (75.0%)	—	30/32	12/12
2.5+	0/32 GARBLED	—	0/32 GARBLED	0/12

Do not exceed alpha=2.25 — the garble cliff between 2.25 and 2.5 is abrupt and total. alpha=2.25 trades 2 benign items for +3 refusal32 points; 2.0 is the last fully-clean point. Cyber transfers near-fully at 2.0.

Usage

Same GLP contract as the Qwen3.8-Flash-Next GLP-47. Note: stock GLM-5.3-Flash already delivers most AdvBench-style prompts; this vector targets the harder refusal32-style phrasing and cyber holdouts.

Content SHA-256 (tensor bytes): 4fc8ec5106a05e8fa9d3c6cd53c28f70dc8d48b62dc3380855602394091f2f3f

Downloads last month: -

GGUF

Model size

721k params

Architecture

controlvector

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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