Downloads · 30 days
416
8% of all-time downloads
morikomorizz/Qwopus3.5-122B-Distill-Kimi-Uncensored-GGUF
Qwopus3.5-122B-Distill-Kimi-Uncensored-GGUF is a text generation model from morikomorizz. Use it when you need the model to write or continue text. It is set up for transformers.
This repository contains the GGUF quantized files for OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated. - Original Model: OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated
Downloads · 30 days
416
8% of all-time downloads
All-time downloads
5.2K
Public
Repo size
210 GB
Likes
4
Public
Click a slice to open those files.
.gguf210 GB · 100%
From the Hugging Face model README
This repository contains the GGUF quantized files for OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated.
| Quant Type | Size | Description |
|---|---|---|
| IQ2_M | 55-59 GB | Mixed Precision for Better Quality |
| IQ3_M | 62-67 GB | Mixed Precision for Better Quality |
| IQ4_NL | 76-81 GB | Mixed Precision for Better Quality |
The pipeline:
B-matrix on residual-write modules after each optimizer step (B := B − r·(rᵀB)), so the LoRA update is forbidden from re-introducing the refusal direction. LoRA rank 32, α 64, 54 protected modules across 27 decoder layers. Verified residual after training: max ‖rᵀB‖₂ = 8.5 × 10⁻¹⁰.Qwen/Qwen3.5-122B-A10B shards. Tensor names, shapes, and config.json schema (Qwen3_5MoeForConditionalGeneration, model_type: qwen3_5_moe) match the base model exactly — so this checkpoint loads anywhere the original loads.Key Properties:
Qwen/Qwen3.5-122B-A10BOn top of the base abliteration + Opus healing, this release adds a focused healing pass built from Kimi K2.6:
The DPO pass targets the language model's reasoning behavior only; the abliteration, vision tower, and MTP head are unchanged by this step.
This model family outperforms the full-precision (BF16) Qwen/Qwen3.5-122B-A10B baseline across reasoning, coding, and tool-use benchmarks:
| Benchmark | Qwen3.5-122B-A10B (BF16, baseline) | Qwopus3.5-122B-A10B |
|---|---|---|
| CTI | 64.8 | 71.5 |
| LiveCodeBench | 78.9 | 79.9 |
| BFCL | 72.2 | 85.6 |
BFCL is the Berkeley Function-Calling Leaderboard (tool use); LiveCodeBench is contamination-controlled code generation.
Use is the responsibility of the user. Ensure your usage complies with applicable laws, platform rules, and deployment requirements.
These GGUF files are fully compatible with llama.cpp and popular graphical interfaces like LM Studio.
llama.cpp CLI:./llama-cli -m /path/to/model/Qwopus3.5-122B-Distill-Kimi-IQ3_M.gguf \
-p "Hello, how are you?" \
-sys "You are a helpful AI" \
-n 4096 \
-c 8192
llama-server :./llama-cli -m /path/to/model/Qwopus3.5-122B-Distill-Kimi-IQ3_M.gguf \
--host 0.0.0.0 \
--port 8080