GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
ansulev
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ansulev
Model Tree
deepreinforce-ai/Ornith-1.0-35B
Input Modalities
Output Modalities
Supported Functionality
A measured, validate-before-ship abliteration:
conv1d outlier repair (FernflowerAI method) — rescaled 2 outlier blocks (layers 36/37, σ 0.10→0.062) before abliteration to prevent coherence collapse.abliterix v1.9: grimjim norm-preserving biprojected abliteration + Expert-Granular Abliteration (EGA) across all 256 fused experts + shared expert + router suppression, Optuna multi-objective search (refusals vs KL). Q/K/V left untouched (attn_output_gate). GatedDeltaNet/SSM internals and the vision tower are not modified.| Metric | Original Ornith-1.0-35B | This model |
|---|---|---|
| Refusals (80 diverse harmful prompts: CBRN, cyber, weapons, self-harm) | high | 0 / 80 (0.0%) |
| Agentic/coding pass@1 (18-task self-contained probe) | 0.833 | 0.833 (identical, family-by-family) |
| First-token KL vs base (abliteration fidelity) | — | ~0.0014 |
| Coherence (benign + harmful, long gen) | — | clean (no degeneration) |
Zero coding-capability degradation (the model's core competency — base Ornith scores Terminal-Bench 2.1 = 64.2, SWE-bench Verified = 75.6) and full refusal removal. This is a near-lossless uncensoring: the abliteration is gentle enough (KL ~0.0014) that capability is preserved, while refusals are eliminated.
bash
vllm serve AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-BF16 \--served-model-name ornith --max-model-len 262144 \--gpu-memory-utilization 0.85 --max-num-batched-tokens 16384 \--mamba-cache-dtype float32 --reasoning-parser qwen3 \--enable-prefix-caching --trust-remote-code
Reasoning model: every turn opens <think>…</think>. Recommended sampling: temperature 0.6, top_p 0.95, top_k 20. Vision (image/video) is inherited from the base and intact; on a vision-enabled deploy, KV cache stays BF16.
This model has had safety refusals removed and will comply with harmful requests. It is released for research into model alignment, red-teaming, and uncensored assistants. You are solely responsible for what you generate and how you use it; comply with all applicable laws. No warranty.
License: MIT (inherited from the base model).