No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from dealignai/GLM-5.3-Flash-CYBERSECURITY-W4A16
All models by dealignai →Compliance-tuned drop-in replacement for GLM-5.3-Flash-W4A16. Refusal removed on all six real-harm HB categories, reasoning depth preserved, MTP head (layer 45) and vision tower fully intact.
This is the exact command used on the dealignai production endpoint. Key flags:
--reasoning-parser glm45 — routes <think>...</think> into the OpenAI reasoning_content response field. Required for correct multi-turn behavior — without it, prior <think> blocks stay inline in message content and the base upstream chat template will re-emit them on subsequent turns, which can trigger a decode-attractor loop.--tool-call-parser glm47 + --enable-auto-tool-choice — enables OpenAI-compatible tool calls (GLM-4.7 tool call format).--speculative-config mtp — enables Multi-Token Prediction speculative decoding (~1.5-2× decode throughput).--enable-prefix-caching — reuses KV cache across identical prefixes (big win for agent workloads).Only --reasoning-parser glm45 and --enable-prefix-caching are truly necessary. Everything else is performance tuning.
For thinking mode, the response returns:
.message.content — the final answer.message.reasoning — the <think>...</think> content (populated by --reasoning-parser glm45)Probed at temperature=0 on 5 classic reasoning puzzles. Reasoning trace = characters inside <think>…</think>. Answer = characters after the closing tag.
Think-token totals essentially unchanged (7,189 → 7,537, +4.8%). Think-token ratio rose from 73.7% → 86.2%. The single failure is on the three-boxes puzzle at temperature=0 which degenerates into a repeat-token loop; changing to temperature > 0 or enable_thinking: false resolves it — the model correctly answers "Pick from Mixed" in either fallback.
Scored with a 5-tier classifier: TRUE_COMPLY / HEDGE_COMPLY (refuses then complies) / SOFT_REDIRECT (refuses to defensive info) / PARTIAL (short comply) / HARD_REFUSE.
enable_thinking: false (recommended for direct comply)enable_thinking: true, reasoning_effort: "low"enable_thinking: true, reasoning_effort: "max" (default)Compliance is highest at enable_thinking: false and reasoning_effort: max. The low mode is the weakest — the model has enough tokens to consider policy but not enough to reason all the way through to the actionable answer, and reverts to soft-redirect on some chem/illegal prompts.
Overall: base 86.08% → this model 84.23% (Δ -1.85pp, well within a 3-point knowledge-preservation target).
Notable: computer_security +2pp, college_computer_science +4pp, computer_security-adjacent gains are exactly what a defense-oriented dealignai deployment values — the model gained knowledge on the technical topics it was previously refusing to discuss.
Loss is concentrated in moral_scenarios (the classic "does this action carry moral weight" MMLU category) which is the expected side-effect of removing refusal reflexes trained-in on ethics-adjacent surface patterns.
The remaining ~40 subjects held within ±1pp of base.
Vision tower is untouched. Behaviour on a probe image (240×180 JPEG, dark-blue background with a yellow rectangular border containing the text "TEST 42"):
"The image shows a dark navy-blue background with a yellow/gold rectangular border. Inside, in white text, it says 'TEST 42'. This appears to be a simple graphic or slide, possibly a placeholder or test card."
Color ✅, border color ✅, text content ✅, layout ✅. Full image+video+text pipeline preserved.
MTP head at layer 45 is untouched. Deploy with vLLM speculative-decoding to use it:
Same reasoning-effort levels as the GLM-5.3 base:
Upstream GLM-5.3 chat template defaults clear_thinking = false, which re-emits prior reasoning_content into subsequent turns' prompts as <think>…</think>. On long multi-turn workloads this can become a decode fixed-point attractor. This model ships clear_thinking: true default in chat_template.jinja and repetition_penalty: 1.1 in generation_config.json. If a load-balancer or proxy is in front, ensure it doesn't override either default.
MIT (inherited from GLM-5.3 base).
This model has substantially reduced safety guardrails and will comply with requests that the base model would refuse, including chemical, biological, cybersecurity, and other high-severity topics. Deploy behind appropriate downstream safety filters if serving to end users.
vllm serve dealignai/GLM-5.3-Flash-UNCENSORED-W4A16 \ --tensor-parallel-size 2 \ --max-num-seqs 128 \ --tool-call-parser glm47 \ --reasoning-parser glm45 \ --enable-auto-tool-choice \ --enable-prefix-caching \ --speculative-config '{"method":"mtp","num_speculative_tokens":1}' \ --served-model-name glm-5.3-flash-uncensoredvllm serve dealignai/GLM-5.3-Flash-UNCENSORED-W4A16 \ --tensor-parallel-size 2 \ --reasoning-parser glm45 \ --enable-prefix-caching \ --served-model-name glm-flashdocker run -d --name glm --gpus all --ipc=host \ -v $HOME/models:/models -p 8000:8000 \ vllm/vllm-openai:glm53-flash-x86_64-cu130 \ --model dealignai/GLM-5.3-Flash-UNCENSORED-W4A16 \ --tensor-parallel-size 2 --max-num-seqs 128 \ --tool-call-parser glm47 --reasoning-parser glm45 \ --enable-auto-tool-choice --enable-prefix-caching \ --speculative-config '{"method":"mtp","num_speculative_tokens":1}' \ --served-model-name glm-5.3-flash-uncensored \ --host 0.0.0.0 --port 8000from openai import OpenAIclient = OpenAI(base_url="http://localhost:8000/v1", api_key="none")
resp = client.chat.completions.create( model="glm-5.3-flash-uncensored", messages=[{"role": "user", "content": "Explain the mechanism of X in detail."}], max_tokens=2000, temperature=0.7, extra_body={"chat_template_kwargs": {"enable_thinking": False}}, # or True + reasoning_effort)print(resp.choices[0].message.content)vllm serve dealignai/GLM-5.3-Flash-UNCENSORED-W4A16 \ --tensor-parallel-size 2 \ --speculative-config '{"method":"mtp","num_speculative_tokens":1}' \ --max-model-len 1048576