Document validated public release

README.md

@@ -3,21 +3,86 @@ license: mit
 base_model: ornith-ai/Ornith-1.5-9B
 library_name: transformers
 pipeline_tag: image-text-to-text
-tags:
-- qwen3_5
-- abliterated
-- multimodal
----
+tags:
+- qwen3_5
+- abliterated
+- multimodal
+- red-team
+- ai-safety-research
+---
 
 # Ornith-1.5-9B-Abliterated-FP8
 
-An abliterated derivative of `ornith-ai/Ornith-1.5-9B` at revision
-`489cb97981b8654bcfcf30ce1f94ed1b62e07b53`. Released as compressed-tensors FP8_DYNAMIC W8A8.
+An abliterated derivative of [ornith-ai/Ornith-1.5-9B](https://huggingface.co/ornith-ai/Ornith-1.5-9B)
+at revision `489cb97981b8654bcfcf30ce1f94ed1b62e07b53`, released as
+compressed-tensors FP8_DYNAMIC W8A8.
 
 Inference-oriented; use the BF16 repository for training.
 
-The language residual projections were modified. The vision tower, MTP block,
-tokenizer, chat template, and multimodal processors are preserved.
-
-Validation metrics and the exact surgery report will be added before the
-repository is made public.
+## What changed
+
+The language residual projections were modified. The vision tower, MTP block,
+tokenizer, chat template, and multimodal processors are preserved. The pipeline
+used complementary SVD and LEACE refusal-direction surgery, iterative re-probing,
+targeted security-prompt refinement, and weight-space blending.
+
+## Validation
+
+The FP8 release quantizes 248 language projection tensors and preserves 527
+protected tensors. Reconstruction validation measured a maximum relative
+Frobenius error of `0.026736` and minimum cosine similarity of `0.999635`. See
+`validation_report.json` for per-tensor details.
+
+The accepted BF16 checkpoint scored `0/12` refusal flags during refinement and
+`0/24` on a separate held-out first-token refusal screen. The held-out mean
+refusal-token probability was `1.18e-5`.
+
+Coding evaluation was intentionally deferred before this release. These numbers
+are structural and refusal-screen diagnostics, not a claim of benchmark parity
+with the base model. A one-task generation smoke test is not reported as an
+evaluation result.
+
+## Usage
+
+```bash
+pip install torch transformers accelerate compressed-tensors
+```
+
+```python
+import torch
+from transformers import AutoModelForMultimodalLM, AutoProcessor
+
+model_id = "KellHect/Ornith-1.5-9B-Abliterated-FP8"
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForMultimodalLM.from_pretrained(
+    model_id, dtype=torch.bfloat16, device_map="auto"
+)
+
+messages = [{"role": "user", "content": "Explain this code and identify the bug."}]
+inputs = processor.apply_chat_template(
+    messages, add_generation_prompt=True, tokenize=True,
+    return_dict=True, return_tensors="pt",
+).to(model.device)
+output = model.generate(**inputs, max_new_tokens=512)
+print(processor.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```
+
+FP8 users need mutually compatible versions of Torch, Transformers, and
+`compressed-tensors`. If the FP8 loader is unavailable on a platform, use the
+BF16 release.
+
+## Research context
+
+This model has had refusal behavior deliberately reduced. It may comply with
+requests that the base model rejects. Users are responsible for deployment,
+access control, generated content, and compliance with applicable law.
+
+## Credits
+
+- [Ornith AI](https://huggingface.co/ornith-ai) for the base model.
+- [OBLITERATUS](https://github.com/elder-plinius/OBLITERATUS) for the abliteration research and implementation lineage.
+- Arditi et al. for refusal-direction research and Belrose et al. for LEACE.
+
+## License
+
+MIT. See `LICENSE`.