license: apache-2.0
base_model:
- YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated
base_model_relation: quantized
pipeline_tag: text-generation
tags: - gguf
- llama.cpp
- qwen3.5
- gated-deltanet
- reasoning
- abliterated
- uncensored
- imatrix
language: - en
- zh
YuYu1015-Ornith-1.0-9B-abliterated-GGUF
GGUF quants of YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated (the BF16 source).
English
imatrix-calibrated, Unsloth-Dynamic-style GGUF quants of the abliterated (uncensored) Qwen3.5 9B dense reasoning model. Sensitive tensors (state-space / GatedDeltaNet, attention, embeddings) are kept at higher precision while the bulk carries the compression — so quality holds up far better than a flat quant.
Files
| Quant | Size | Notes |
|---|---|---|
| Q8_0 | 9.53 GB | Near-lossless, highest quality |
| UD-Q6_K | 7.95 GB | High quality |
| UD-Q4_K_M | 6.20 GB | Best size/quality balance — recommended for most |
- UD = imatrix (chat+code+wiki calibration) + per-tensor dynamic precision:
ssm_*(GatedDeltaNet) → Q8_0, attention → Q5_K (in Q4_K_M), output/embeddings kept high. - BF16 source: YuYu1015-Ornith-1.0-9B-abliterated
Requirements
Use the latest llama.cpp — Qwen3.5's hybrid GatedDeltaNet / SSM layers need recent operators.
Recommended Sampling Parameters
Reasoning model (emits <think>…</think>). Official Qwen3.5 settings:
--temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0 --repeat-penalty 1.05
The 9B benefits from a small
repeat-penalty 1.05(unlike the 35B, which uses 1.0).
Usage (llama.cpp)
llama-cli -m Ornith-9B-UD-Q4_K_M.gguf --temp 1.0 --top-p 0.95 --top-k 20 --repeat-penalty 1.05 -cnv
Safety Warning
This model has safety filtering removed (abliterated) and may generate sensitive or inappropriate content. Users are solely responsible for all consequences and legal liability, and must ensure usage complies with local laws and ethical standards.
Credits
- BF16 source: YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated
- Base model: deepreinforce-ai/Ornith-1.0-9B
- Author: YuYu1015
繁體中文
YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated(BF16 來源)的 GGUF 量化版本。
以 imatrix 高校準 + Unsloth-Dynamic 風格量化的 abliterated(去審查)Qwen3.5 9B dense 推理模型。敏感張量(state-space / GatedDeltaNet、attention、embedding)保高精度,壓縮集中在主體 —— 品質遠優於整體單一量化。
檔案
| 量化 | 大小 | 說明 |
|---|---|---|
| Q8_0 | 9.53 GB | 近乎無損,最高品質 |
| UD-Q6_K | 7.95 GB | 高品質 |
| UD-Q4_K_M | 6.20 GB | 大小/品質最佳平衡 —— 多數人推薦 |
- UD = imatrix(chat+code+wiki 校準)+ 逐張量動態精度:
ssm_*(GatedDeltaNet)→ Q8_0、attention → Q5_K(Q4_K_M 中)、output/embedding 保高。 - BF16 來源: -9B-abliterated
需求
請用最新 llama.cpp —— Qwen3.5 的 GatedDeltaNet / SSM 混合層需要新算子。
建議取樣參數
推理模型(輸出 <think>…</think>)。Qwen3.5 官方設定:
--temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.0 --repeat-penalty 1.05
9B 建議用小幅
repeat-penalty 1.05(與 35B 用 1.0 不同)。
使用方式(llama.cpp)
llama-cli -m Ornith-9B-UD-Q4_K_M.gguf --temp 1.0 --top-p 0.95 --top-k 20 --repeat-penalty 1.05 -cnv
安全警告
此模型已移除安全過濾(abliterated),可能產生敏感或不當內容。使用者須自行承擔所有風險與法律責任,並確保使用方式符合當地法規與倫理標準。
致謝
- BF16 來源: YuYu1015/YuYu1015-Ornith-1.0-9B-abliterated
- 基礎模型: deepreinforce-ai/Ornith-1.0-9B
- 作者: YuYu1015