Downloads · 30 days
3.7K
7% of all-time downloads
0xKitkat/Ornith-1.5-35B-A3B-Uncensored-GGUF
Ornith-1.5-35B-A3B-Uncensored-GGUF is a image-text-to-text model from 0xKitkat. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Follow @procrastiness on Twitter for new model releases and updates.
Downloads · 30 days
3.7K
7% of all-time downloads
All-time downloads
52.2K
Public
Repo size
119 GB
Likes
8
Trending 1
Click a slice to open those files.
.gguf119 GB · 100%
From the Hugging Face model README
Follow @procrastiness on Twitter for new model releases and updates.
An uncensored derivative of ornith-ai/Ornith-1.5-35B-A3B, preserving Ornith's coding/agentic post-training, native vision tower, 262K context configuration, and native multi-token-prediction (MTP) head.
This is a streamed task-vector transplant, not a prompt wrapper:
output = Ornith-1.5 + 1.0 * (Qwen3.6-Abliterated - Qwen3.6-Base)
The donor delta comes from wangzhang/Qwen3.6-35B-A3B-abliterated, whose card documents rank-1 attention/MLP steering, expert-granular abliteration, router suppression, orthogonalization, and Gaussian layer decay. Applying its low-KL Qwen task vector to Ornith is intended to transfer refusal suppression without replacing Ornith's self-improvement RL and coding specialization.
Only exact name-and-shape-compatible tensors were eligible:
All arithmetic was performed in float32 and rounded once to the target BF16 dtype. Target-only vision/MTP tensors were copied unchanged.
e4dfb35a93d4b6822a811a7676f3488514abe7e2995ad96eacd98c81ed38be0c5b274b04031597b013db4501cbaf158956f470a990101500ad825f641.0The machine-readable task_vector_report.json contains per-shard SHA-256 hashes
and the 100 tensors with the largest relative deltas.
True| File | Format | Size |
|---|---|---|
mmproj-Ornith-1.5-35B-Uncensored-BF16.gguf | Vision projector | 0.84 GiB |
Ornith-1.5-35B-Uncensored-BF16.gguf | BF16 | 66.19 GiB |
Ornith-1.5-35B-Uncensored-Q4_K_M.gguf | Q4_K_M | 20.22 GiB |
Ornith-1.5-35B-Uncensored-Q5_K_M.gguf | Q5_K_M | 23.61 GiB |
The release was tested through llama.cpp on the Q4_K_M build. Full details and
raw generations are included in evaluation_report.json.
llama-server -hf 0xKitkat/Ornith-1.5-35B-A3B-Uncensored-GGUF:Q4_K_M \
--jinja --reasoning-format deepseek --port 8000
For image input, also load mmproj-Ornith-1.5-35B-Uncensored-BF16.gguf.
Recommended upstream sampling: temperature=0.6, top_p=0.95, top_k=20.
Ornith is a reasoning model and emits <think>...</think> before the answer.
"Uncensored" means the refusal behavior was deliberately reduced. It does not mean every request will be answered, nor that upstream benchmark scores are guaranteed unchanged. Ornith's published benchmark table has not been claimed as a benchmark of this derivative; use the included build and evaluation reports for claims specific to this release.
The Qwen Apache-2.0 license and upstream notices are included with the release.