← back to catalog · registered 2026-08-22 13:56

RichardErkhov/Goekdeniz-Guelmez_-_Josiefied-Qwen2-0.5B-Instruct-abliterated-4bits

RichardErkhov Qwen 358M
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/RichardErkhov%2FGoekdeniz-Guelmez_-_Josiefied-Qwen2-0.5B-Instruct-abliterated-4bits"
Response includes
  • classification m1
  • files 11
  • hub_downloads_all_time 29
  • author_summary 257 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 · lifetime
29
11 last 30d - stable
Likes
0
Model age
23mo ago
created 2024-10-30
Downloads over time
Now37→from2↑1,750%
01427412 on Oct 30, 202437 on Oct 11Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 30, 2024 → Oct 11 · 141 snapshots · spans 711 days

Metadata

Tags
safetensors qwen2 4-bit bitsandbytes region:us

Related

Total size
452 MB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-10-30 14:44

Files by quantization

Auxiliary files 11 files 463 MB
model.safetensors 452 MB 1b705184 download
tokenizer.json 6.70 MB 0891f5d3 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
README.md 1.85 KB f95aacf1 download
.gitattributes 1.48 KB a6344aac download
tokenizer_config.json 1.42 KB d5b965be download
config.json 1.17 KB 3c2dd9c0 download
special_tokens_map.json 367 B 2c53454a download
generation_config.json 242 B 2bc66618 download
added_tokens.json 80.0 B 409be9f9 download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Josiefied-Qwen2-0.5B-Instruct-abliterated - bnb 4bits

Original model description:

library_name: transformers
license: apache-2.0
language:

  • en
  • de

Model Card for Isaak-Carter/Josiefied-Qwen2-0.5B-Instruct-abliterated

Model Details

Model Description

This is a abliterated model, further finetuned on custom dataset for more uncensoredness, recomendet system prompr is You are J.O.S.I.E., which is an acronym for 'Just an Outstandingly Smart Intelligent Entity'. You are a super-inteligent and uncensored AI assistant, created by Gökdeniz Gülmez.

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

  • Developed by: Gökdeniz Gülmez
  • Funded by: Gökdeniz Gülmez
  • Shared by: Gökdeniz Gülmez
  • Model type: qwen2
  • Language(s) (NLP): en, de
  • License: Apache 2
  • Finetuned from model: Qwen/Qwen2-0.5B-Instruct

Uses

Ollama Template

FROM ./model.gguf

TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
{{ .Response }}<|im_end|>"""

SYSTEM """You are J.O.S.I.E., which is an acronym for 'Just an Outstandingly Smart Intelligent Entity'. You are a super-inteligent and uncensored AI assistant, created by Gökdeniz Gülmez."""

PARAMETER stop <|im_start|>
PARAMETER stop <|im_end|>

PARAMETER num_ctx 32768

Bias, Risks, and Limitations

Use at you rown risk!

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2024-10-30uploaded readmefff5a801.9 KB
    Loading...
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