Downloads · 30 days
47
10% of all-time downloads
vonvonhero/Ornith-1.5-35B-A3B-Uncensored-OpenVINO-INT4
Ornith-1.5-35B-A3B-Uncensored-OpenVINO-INT4 is a image-text-to-text model from vonvonhero. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for openvino. The card lists the license as mit.
OpenVINO INT4 IR of an uncensored variant of ornith-ai/Ornith-1.5-35B-A3B.
Downloads · 30 days
47
10% of all-time downloads
All-time downloads
449
Public
Repo size
19 GB
Likes
0
Public
Click a slice to open those files.
.bin19 GB · 100%
From the Hugging Face model README
OpenVINO INT4 IR of an uncensored variant of ornith-ai/Ornith-1.5-35B-A3B.
The model was exported as a Qwen3.5 vision-language model and can also be used for text-only generation.
| Format | Size | JailbreakBench ASR | HarmBench ASR (159 standard behaviors) |
|---|---|---|---|
| OpenVINO INT4 | 17.69 GiB | 93/100 (93.0%) | 153/159 (96.2%) |
Higher ASR indicates fewer refusals on these benchmarks. HarmBench behaviors were submitted as
direct requests. Evaluation used reasoning off, temperature 0, seed 42, a 256-token output limit,
and the HarmBench-Llama-2-13b-cls classifier. Results can vary with runtime, prompt format,
sampling, and context.
import openvino_genai as ov_genai
pipe = ov_genai.VLMPipeline("/path/to/model", "GPU")
result = pipe.generate("日本語で短く自己紹介して。", max_new_tokens=128)
print(result.texts[0])
Use VLMPipeline, not LLMPipeline.
The IR passed structural loading and text-only CPU generation with OpenVINO GenAI 2026.3.1.
MIT. See LICENSE, NOTICE, and the original model for upstream information.