GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
pidof
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
pidof
Model Tree
Qwen/Qwen3-32B
Input Modalities
Output Modalities
Supported Functionality
Heretic ran 200 Optuna trials and this checkpoint is the Pareto-optimal trial with the fewest refusals (trial 191). Refusals were measured on 100 held-out harmful prompts; KL divergence was measured on harmless prompts against the original model, so lower means closer to the original.
| Metric | This model | Original Qwen3-32B |
|---|---|---|
| Refusals (of 100 harmful test prompts) | 20 | 100 |
| KL divergence from original | 0.0919 | 0 (by definition) |
A KL divergence under 0.1 indicates the model's general capabilities are essentially intact. Heretic's guidance is that values above 0.5 usually indicate significant damage; this model is well below that. Refusals were reduced by 80%, not eliminated. Some prompts will still be declined.
| Component | max_weight | max_weight_position | min_weight | min_weight_distance |
|---|---|---|---|---|
| attn.o_proj | 1.4996 | 39.46 | 1.2006 | 37.70 |
| mlp.down_proj | 1.4219 | 39.39 | 0.0965 | 36.19 |
Model has 64 layers; positions and distances are in layer units. The refusal direction was selected
per layer (direction_index = None).
Qwen3 supports a thinking mode. Heretic evaluated refusals with thinking disabled
(responses were prefixed with an empty <think></think> block). Behaviour with thinking enabled
was not measured and may differ. For the most predictable results, use enable_thinking=False
or call with /no_think.
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "pidof/Qwen3-32B-heretic"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype="bfloat16", device_map="auto") messages = [{"role": "user", "content": "Explain how a buffer overflow works."}]inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, enable_thinking=False, return_tensors="pt").to(model.device)out = model.generate(inputs, max_new_tokens=512)print(tokenizer.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))bash
vllm serve pidof/Qwen3-32B-heretic --dtype bfloat16 --max-model-len 32768The checkpoint is 65.5 GB in bfloat16 and fits on a single 80 GB GPU or any device with at least ~70 GB of unified memory. Quantized variants can be made with the usual tools (llama.cpp, AWQ, GPTQ); abliteration does not interfere with quantization.
--export-strategy mergeThis model follows user instructions with far fewer refusals than the original. It is intended for research on safety training, red-teaming, creative writing, and other settings where the base model's refusals get in the way of legitimate work. It inherits every limitation of Qwen3-32B, including hallucination, and it will comply with harmful requests more readily than the original. You are responsible for how you deploy it. Add your own moderation layer if you serve it to others.
Apache 2.0, the same as the base model. Qwen3-32B is Copyright Alibaba Cloud. Heretic is AGPL-3.0, which covers the tool, not the weights it produces.
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "pidof/Qwen3-32B-heretic"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype="bfloat16", device_map="auto") messages = [{"role": "user", "content": "Explain how a buffer overflow works."}]inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, enable_thinking=False, return_tensors="pt").to(model.device)out = model.generate(inputs, max_new_tokens=512)print(tokenizer.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))vllm serve pidof/Qwen3-32B-heretic --dtype bfloat16 --max-model-len 32768