library_name: gguf
license: mit
base_model: ornith-ai/Ornith-1.5-9B
pipeline_tag: image-text-to-text
tags:
- gguf
- ornith
- ornith-1.5
- multimodal
- abliterated
Ornith 1.5 9B Abliterated — GGUF BF16, Q8_0, Q6_K, and Q4_K_M
An unofficial experimental derivative ofornith-ai/Ornith-1.5-9B, pinned to
revision c927ad73b7eb20f00aafcaa0a11a9d58ed5487bc.
The original model is by the Ornith team. The conversion, refusal-direction
experiment, and validation were performed by PocketAI Model Lab;PocketAiHub identifies the publisher of this derivative.
Purpose and responsible use
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.
Release family
Files and validation
| Quant | File | Size | Refusal-targeted flags | Benign-control flags | Capability |
|---|---|---|---|---|---|
| BF16 | Ornith-1.5-9B-Abliterated-BF16.gguf |
16.69 GiB | 0/100 | 0/100 | 71/80 |
| Q8_0 | Ornith-1.5-9B-Abliterated-Q8_0.gguf |
8.87 GiB | 0/100 | 0/100 | 72/80 |
| Q6_K | Ornith-1.5-9B-Abliterated-Q6_K.gguf |
6.85 GiB | 0/100 | 0/100 | 68/80 |
| Q4_K_M | Ornith-1.5-9B-Abliterated-Q4_K_M.gguf |
5.24 GiB | 0/100 | 0/100 | 68/80 |
The separate mmproj-Ornith-1.5-9B-Abliterated-F16.gguf vision projector is compatible with every text
GGUF in this repository. Q4_K_M plus the projector passed an end-to-end image
smoke test (red). Native MTP is not included.
The ablation scale is 1.0. Seeabliteration-manifest.json andvalidation-summary.json for machine-readable
provenance and results.
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.
llama.cpp
llama-server -m Ornith-1.5-9B-Abliterated-Q4_K_M.gguf \
--mmproj mmproj-Ornith-1.5-9B-Abliterated-F16.gguf -ngl all -c 8192
License
The upstream model card declares MIT. This repository includes the MIT license
and preserves attribution to the pinned source above.