GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
harrrshall
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
harrrshall
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForImageTextToText, AutoProcessorbase_id = "Qwen/Qwen3.5-4B"base_revision = "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a"processor = AutoProcessor.from_pretrained(base_id, revision=base_revision)base = AutoModelForImageTextToText.from_pretrained(base_id,revision=base_revision,dtype=torch.bfloat16,device_map="auto",)model = PeftModel.from_pretrained(base, "harrrshall/lumen")model.eval()
do not download both editions. choose lumen-merged for a simple standalone setup, or this adapter when you already store the pinned base model and want the smaller download.
Lumen generates small structured patches for automatically verifiable accessibility defects in react and static html source code.
| field | value |
|---|---|
| model name | Lumen |
| base model | qwen3.5 4b |
| training method | qlora supervised fine tuning |
| working context | 16,384 tokens |
| output | structured source patch |
| license | apache 2.0 |
| system | tasks | saferepair | cost per safe repair |
|---|---|---|---|
| Lumen | 43 tasks | 42/43 (97.67%) | $0.000268 |
| gpt-5.6 sol | 43 tasks | 40/43 (93.02%) | $0.070857 |
| claude opus 4.8 | 43 tasks | 43/43 (100%) | $0.054012 |
browser saferepair requires target findings to be removed without new findings, plus passing builds, selected tests, keyboard and focus checks, semantic and functional invariants, visual policy, protected path checks, and evaluator evasion controls.
the current synthetic corpus contains 637 verified training tasks, 100 development tasks, and 100 sealed synthetic tasks. the trajectory set contains 30,576 training records and 100 development records. a11ybench is reserved for evaluation and excluded from training.
Lumen covers deterministic source repair families supported by its evaluator. it does not establish complete wcag or legal conformance. review every patch before merging, and involve qualified accessibility practitioners and assistive technology users for subjective decisions.