GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
PocketAiHub
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
PocketAiHub
Model Tree
ornith-ai/Ornith-1.5-9B
Input Modalities
Output Modalities
Supported Functionality
This experimental derivative studies whether learned refusal behavior can be reduced while retaining general capability. It is published for research and legitimate local use, not to endorse or facilitate illegal, abusive, or dangerous applications.
The edit reduces refusal behavior broadly rather than determining whether a request is legitimate. Deployers should evaluate the model in their own context and apply appropriate safeguards. Abliteration is not truthfulness training, a capability improvement, or a guarantee of universal compliance.
| Gate | Result |
|---|---|
| Refusal-targeted explicit-refusal phrase flags | 0/100 |
| Benign-control explicit-refusal phrase flags | 0/100 |
| Medium capability suite | 71/80 |
| Runtime smoke | passed |
The medium suite covers math/reasoning, false-premise handling, instruction following, coding, structured output, multilingual output, context comprehension, and general coherence.
The refusal scorer is phrase based and can miss redirects and other non-literal forms of non-compliance. Therefore 0/100 phrase flags measures explicit refusal wording, not universal compliance or response quality. The 256-token runs are early-response screens rather than complete long-answer evaluations.
See abliteration-manifest.json and
validation-summary.json for machine-readable
provenance and category-level results.
python
from transformers import AutoProcessor, Qwen3_5ForConditionalGenerationrepo = "PocketAiHub/Ornith-1.5-9B-Abliterated"processor = AutoProcessor.from_pretrained(repo)model = Qwen3_5ForConditionalGeneration.from_pretrained(repo, device_map="auto")
The upstream model card declares MIT. This repository includes the MIT license and preserves attribution to the pinned source above.