GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
willmargs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
willmargs
Model Tree
Qwen/Qwen3.8-27B
Input Modalities
Output Modalities
Supported Functionality
| Measure | Base model | This weight edit |
|---|---|---|
| Multiple-choice arithmetic correct | 189/252 (75.0%) | 197/252 (78.2%) |
| Numeric-answer arithmetic correct | 63/63 (100%) | 63/63 (100%) |
| Adult-fiction willingness refusals | 64/64 | 0/64 |
The MCQ result is a net improvement of eight correct answers: 15 base-model mistakes were fixed and seven previously correct answers became incorrect. The numeric-answer set uses different questions from the multiple-choice set.
Measurements characterize this BF16 weight-edit configuration. Uploaded files were integrity-checked, but no separate inference benchmark was run after upload. Detailed evaluation data are available in the report and the evaluation summary.
Use sufficient GPU memory for the BF16 checkpoint or supported device offloading. The evaluation runtime used Torch 2.10.0 and Transformers 5.17.0, with flash-linear-attention 0.5.2 for fast linear-attention kernels.
python
import osimport torchfrom transformers import AutoTokenizer, AutoModelForImageTextToText repo = "willmargs/Qwen3.8-27B-abliterated-arithmetic-tradeoff"# Supply HF_TOKEN securely in the process environment for private-repo access.token = os.environ["HF_TOKEN"]tokenizer = AutoTokenizer.from_pretrained(repo, token=token)model = AutoModelForImageTextToText.from_pretrained( repo, token=token, dtype=torch.bfloat16, device_map="auto").eval()text = tokenizer.apply_chat_template( [{"role": "user", "content": "Calculate 17 + 24. Reply only with the number."}], tokenize=False, add_generation_prompt=True, enable_thinking=False,)inputs = tokenizer(text, return_tensors="pt", add_special_tokens=False).to(model.device)with torch.inference_mode(): output = model.generate(**inputs, do_sample=False, max_new_tokens=32)print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))Quantizing these weights is a separate transformation and may change behavior.
The edit projects a shared direction out of 129 text residual-write matrices (input embeddings, attention outputs, and MLP down-projections). The original architecture, tokenizer, vision weights, and license are retained. This does not establish a unique refusal neuron or mechanism.
Base model: Qwen/Qwen3.8-27B. Original model card: BASE_MODEL_README.md. License: LICENSE. Modified weights published by willmargs. Method background: Refusal in Language Models Is Mediated by a Single Direction.
import osimport torchfrom transformers import AutoTokenizer, AutoModelForImageTextToText repo = "willmargs/Qwen3.8-27B-abliterated-arithmetic-tradeoff"# Supply HF_TOKEN securely in the process environment for private-repo access.token = os.environ["HF_TOKEN"]tokenizer = AutoTokenizer.from_pretrained(repo, token=token)model = AutoModelForImageTextToText.from_pretrained( repo, token=token, dtype=torch.bfloat16, device_map="auto").eval()text = tokenizer.apply_chat_template( [{"role": "user", "content": "Calculate 17 + 24. Reply only with the number."}], tokenize=False, add_generation_prompt=True, enable_thinking=False,)inputs = tokenizer(text, return_tensors="pt", add_special_tokens=False).to(model.device)with torch.inference_mode(): output = model.generate(**inputs, do_sample=False, max_new_tokens=32)print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))