← back to catalog · registered 2026-11-13 21:03

977895k/occamy-1.0-abliterated-safetensors

977895k Qwen MoE multimodal
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/977895k%2Foccamy-1.0-abliterated-safetensors"
Response includes
  • classification m1
  • files 25
  • benchmarks 11 entries
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
0
Likes
0
Descendants
2
in 2 direct forks
Model age
1w ago
created 2026-11-13
Downloads over time
Now 0 → from 0 ↑ 0%
0011 0 on Nov 13 0 on Nov 15 Nov
Nov 13 → Nov 15 · 3 snapshots · spans 2 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 1.4 UGI
Hazardous 0 UGI
Natural Intelligence 25.43 UGI
Political lean -19.6% UGI
Sensitive-Info 14.03 UGI
SocPol 2.6 UGI
UGI 16.02 UGI
Willingness (10) 2 UGI
W10-Adherence 0 UGI
W10-Direct 4 UGI
Writing 35.83 UGI

Genealogy 2 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5_moe image-text-to-text agent agentic co-work tool-use long-context mixture-of-experts coding abliterated

Related

Total size
65.4 GB
Files
25
Quantizations
1
Registered
2026-11-13 21:03
Last updated on HF
2026-11-14 17:40

Files by quantization

Auxiliary files 25 files 65.5 GB
model-00008-of-00013.safetensors 5.00 GB bbe0ce3d download
model-00003-of-00013.safetensors 5.00 GB db848c43 download
model-00005-of-00013.safetensors 5.00 GB f1817fd7 download
model-00010-of-00013.safetensors 5.00 GB 1ba32ddc download
model-00000-of-00013.safetensors 5.00 GB 4d055792 download
model-00007-of-00013.safetensors 5.00 GB a297accf download
model-00006-of-00013.safetensors 5.00 GB a402eac4 download
model-00011-of-00013.safetensors 5.00 GB b0f226cc download
model-00004-of-00013.safetensors 5.00 GB dfd0aad6 download
model-00009-of-00013.safetensors 5.00 GB 5dec9909 download
model-00002-of-00013.safetensors 5.00 GB 2adffd60 download
model-00001-of-00013.safetensors 5.00 GB 68352233 download
model-00012-of-00013.safetensors 4.57 GB b71ac198 download
model-visual.safetensors 852 MB f730cecc download
tokenizer.json 19.1 MB 06b95093 download
model.safetensors.index.json 3.18 MB 0226b4d0 download
model_index.json 3.18 MB 0226b4d0 download
chat_template.jinja 7.58 KB a8755d82 download
config.json 3.17 KB 9aa5a25e download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.16 KB 33818c7f download
tokenizer_config.json 1.14 KB 1d134cd2 download
README.md 944 B 84b3ebca download
preprocessor_config.json 390 B 2ea84a43 download
LICENSE 157 B 14f93ab8 download

README current version from Hugging Face


license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
base_model: Qwen/Qwen3.6-35B-A3B
tags:

  • agent
  • agentic
  • co-work
  • tool-use
  • long-context
  • mixture-of-experts
  • coding
  • abliterated
  • uncensored

Occamy-1.0 (Abliterated) - Safetensors

This repository provides the abliterated / uncensored weights for Occamy-1.0 in standard Hugging Face .safetensors format (unquantized BF16).

Overview

  • Base Architecture: Qwen/Qwen3.6-35B-A3B / Occamy-1.0 (35B MoE with 3B active params per token)
  • Format: Hugging Face Safetensors (BF16, sharded)
  • Features:
    • Full multimodal vision support (model-visual.safetensors)
    • Safety refusal vectors mathematically abliterated for agentic autonomy and direct code execution
    • Pure standard autoregressive layout (no MTP dependency)
    • Drop-in compatible with vLLM, SGLang, Hugging Face Transformers, and standard local loaders.
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration