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

RichardErkhov/Goekdeniz-Guelmez_-_Josiefied-Qwen2-0.5B-Instruct-abliterated-gguf

RichardErkhov Qwen 500M GGUF 33K ctx
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-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 3,011
  • author_summary 257 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 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.
  • author=richarderkhov (M8 quantization producer)
  • is_gguf=1
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
3K
527 last 30d - stable
Likes
0
Model age
24mo ago
created 2024-10-15
Downloads over time
Now3.1K→from0↑0%
01.1K2.3K3.4K0 on Oct 9, 20243.1K on Oct 113.1K on Oct 10Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 9, 2024 → Oct 11 · 144 snapshots · spans 732 days

Variants by this author 2 formats · 541 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Quantizations
IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0
Tags
gguf endpoints_compatible region:us conversational

Related

Total size
9.78 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2024-10-15 14:14

Files by quantization

Q8_0 1 file 644 MB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q8_0.gguf 644 MB c242fbfd download
Q6_K 1 file 620 MB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q6_K.gguf 620 MB 2665d320 download
Q5_K 3 files 1.45 GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q5_K.gguf 498 MB 7f5728b3 download
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q5_K_M.gguf 498 MB 7f5728b3 download
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q5_K_S.gguf 491 MB cd2ed44c download
Q5 2 files 965 MB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q5_1.gguf 497 MB 6c4d824b download
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q5_0.gguf 468 MB 5a585d83 download
Q4_K 3 files 1.36 GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q4_K.gguf 469 MB fd83a3fc download
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q4_K_M.gguf 469 MB fd83a3fc download
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q4_K_S.gguf 457 MB 1e1f6bb6 download
Q4 2 files 847 MB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q4_1.gguf 438 MB e6de2a85 download
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q4_0.gguf 409 MB 62e94820 download
Q3_K 4 files 1.61 GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q3_K_L.gguf 425 MB cf095123 download
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q3_K.gguf 412 MB 9c571876 download
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q3_K_M.gguf 412 MB 9c571876 download
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q3_K_S.gguf 396 MB 3486c1a9 download
IQ4 2 files 819 MB
Josiefied-Qwen2-0.5B-Instruct-abliterated.IQ4_NL.gguf 411 MB 6e353df2 download
Josiefied-Qwen2-0.5B-Instruct-abliterated.IQ4_XS.gguf 408 MB 5750138a download
IQ3 3 files 1.16 GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.IQ3_M.gguf 400 MB d1fb9c0e download
Josiefied-Qwen2-0.5B-Instruct-abliterated.IQ3_S.gguf 396 MB 19853c9b download
Josiefied-Qwen2-0.5B-Instruct-abliterated.IQ3_XS.gguf 396 MB f2d5d9f9 download
Q2_K 1 file 396 MB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q2_K.gguf 396 MB a4cf6131 download
Auxiliary files 2 files 10.5 KB
README.md 7.14 KB 0dc40f2a download
.gitattributes 3.40 KB b99d159a download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Josiefied-Qwen2-0.5B-Instruct-abliterated - GGUF

Name Quant method Size
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q2_K.gguf Q2_K 0.39GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.IQ3_XS.gguf IQ3_XS 0.39GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.IQ3_S.gguf IQ3_S 0.39GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q3_K_S.gguf Q3_K_S 0.39GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.IQ3_M.gguf IQ3_M 0.39GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q3_K.gguf Q3_K 0.4GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q3_K_M.gguf Q3_K_M 0.4GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q3_K_L.gguf Q3_K_L 0.42GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.IQ4_XS.gguf IQ4_XS 0.4GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q4_0.gguf Q4_0 0.4GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.IQ4_NL.gguf IQ4_NL 0.4GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q4_K_S.gguf Q4_K_S 0.45GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q4_K.gguf Q4_K 0.46GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q4_K_M.gguf Q4_K_M 0.46GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q4_1.gguf Q4_1 0.43GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q5_0.gguf Q5_0 0.46GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q5_K_S.gguf Q5_K_S 0.48GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q5_K.gguf Q5_K 0.49GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q5_K_M.gguf Q5_K_M 0.49GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q5_1.gguf Q5_1 0.49GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q6_K.gguf Q6_K 0.61GB
Josiefied-Qwen2-0.5B-Instruct-abliterated.Q8_0.gguf Q8_0 0.63GB

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. 2024-10-15uploaded readme8e483e17.1 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