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

RichardErkhov/Orion-zhen_-_Qwen2.5-7B-Instruct-Uncensored-gguf

RichardErkhov Qwen 7B 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%2FOrion-zhen_-_Qwen2.5-7B-Instruct-Uncensored-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 6,915
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=RichardErkhov
All 257 models by RichardErkhov
 GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
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
How we label → About M8 →
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
7K
1K last 30d - stable
Likes
3
Model age
24mo ago
created 2024-10-18
Downloads over time
Now7.2K→from638↑1,029%
02.6K5.3K7.9K638 on Oct 16, 20247.2K on Oct 11Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 16, 2024 → Oct 11 · 143 snapshots · spans 725 days

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

Other by RichardErkhov
byroneverson_-_gemma-2-27b-it-abliterated-gguf 2K huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-gguf 2K failspy_-_Codestral-22B-v0.1-abliterated-v3-gguf 2K Rupesh2_-_Llama-3.1-8B-Uncensored-gguf 2K huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf 2K
Total size
95.1 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2024-10-18 18:33
Source huggingface.co/RichardErkhov/Orion-zhen_-_Qwen2.5-7B-Instruct-Uncensored-gguf ↗

Files by quantization

Q8_0 1 file 7.54 GB
Qwen2.5-7B-Instruct-Uncensored.Q8_0.gguf 7.54 GB ba2ba45d download
Q6_K 1 file 5.82 GB
Qwen2.5-7B-Instruct-Uncensored.Q6_K.gguf 5.82 GB bdd761b6 download
Q5 2 files 10.3 GB
Qwen2.5-7B-Instruct-Uncensored.Q5_1.gguf 5.36 GB 681b5bf8 download
Qwen2.5-7B-Instruct-Uncensored.Q5_0.gguf 4.95 GB 678abad8 download
Q5_K 3 files 15.1 GB
Qwen2.5-7B-Instruct-Uncensored.Q5_K.gguf 5.07 GB 229bcb4f download
Qwen2.5-7B-Instruct-Uncensored.Q5_K_M.gguf 5.07 GB 229bcb4f download
Qwen2.5-7B-Instruct-Uncensored.Q5_K_S.gguf 4.95 GB 10eecdd0 download
Q4 2 files 8.67 GB
Qwen2.5-7B-Instruct-Uncensored.Q4_1.gguf 4.54 GB a3b08777 download
Qwen2.5-7B-Instruct-Uncensored.Q4_0.gguf 4.13 GB e4901229 download
Q4_K 3 files 12.9 GB
Qwen2.5-7B-Instruct-Uncensored.Q4_K.gguf 4.36 GB 13d480fb download
Qwen2.5-7B-Instruct-Uncensored.Q4_K_M.gguf 4.36 GB 13d480fb download
Qwen2.5-7B-Instruct-Uncensored.Q4_K_S.gguf 4.15 GB acd592d3 download
IQ4 2 files 8.12 GB
Qwen2.5-7B-Instruct-Uncensored.IQ4_NL.gguf 4.16 GB e414ec48 download
Qwen2.5-7B-Instruct-Uncensored.IQ4_XS.gguf 3.96 GB d3dc4fda download
Q3_K 4 files 14.2 GB
Qwen2.5-7B-Instruct-Uncensored.Q3_K_L.gguf 3.81 GB 105d268a download
Qwen2.5-7B-Instruct-Uncensored.Q3_K.gguf 3.55 GB a55658cd download
Qwen2.5-7B-Instruct-Uncensored.Q3_K_M.gguf 3.55 GB a55658cd download
Qwen2.5-7B-Instruct-Uncensored.Q3_K_S.gguf 3.25 GB ab129201 download
IQ3 3 files 9.70 GB
Qwen2.5-7B-Instruct-Uncensored.IQ3_M.gguf 3.33 GB 220b1505 download
Qwen2.5-7B-Instruct-Uncensored.IQ3_S.gguf 3.26 GB ab1c69c8 download
Qwen2.5-7B-Instruct-Uncensored.IQ3_XS.gguf 3.12 GB d1ee7203 download
Q2_K 1 file 2.81 GB
Qwen2.5-7B-Instruct-Uncensored.Q2_K.gguf 2.81 GB a017f49c download
Auxiliary files 2 files 9.14 KB
README.md 5.98 KB 8d2b818d download
.gitattributes 3.16 KB fcbd2820 download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Qwen2.5-7B-Instruct-Uncensored - GGUF

Name Quant method Size
Qwen2.5-7B-Instruct-Uncensored.Q2_K.gguf Q2_K 2.81GB
Qwen2.5-7B-Instruct-Uncensored.IQ3_XS.gguf IQ3_XS 3.12GB
Qwen2.5-7B-Instruct-Uncensored.IQ3_S.gguf IQ3_S 3.26GB
Qwen2.5-7B-Instruct-Uncensored.Q3_K_S.gguf Q3_K_S 3.25GB
Qwen2.5-7B-Instruct-Uncensored.IQ3_M.gguf IQ3_M 3.33GB
Qwen2.5-7B-Instruct-Uncensored.Q3_K.gguf Q3_K 3.55GB
Qwen2.5-7B-Instruct-Uncensored.Q3_K_M.gguf Q3_K_M 3.55GB
Qwen2.5-7B-Instruct-Uncensored.Q3_K_L.gguf Q3_K_L 3.81GB
Qwen2.5-7B-Instruct-Uncensored.IQ4_XS.gguf IQ4_XS 3.96GB
Qwen2.5-7B-Instruct-Uncensored.Q4_0.gguf Q4_0 4.13GB
Qwen2.5-7B-Instruct-Uncensored.IQ4_NL.gguf IQ4_NL 4.16GB
Qwen2.5-7B-Instruct-Uncensored.Q4_K_S.gguf Q4_K_S 4.15GB
Qwen2.5-7B-Instruct-Uncensored.Q4_K.gguf Q4_K 4.36GB
Qwen2.5-7B-Instruct-Uncensored.Q4_K_M.gguf Q4_K_M 4.36GB
Qwen2.5-7B-Instruct-Uncensored.Q4_1.gguf Q4_1 4.54GB
Qwen2.5-7B-Instruct-Uncensored.Q5_0.gguf Q5_0 4.95GB
Qwen2.5-7B-Instruct-Uncensored.Q5_K_S.gguf Q5_K_S 4.95GB
Qwen2.5-7B-Instruct-Uncensored.Q5_K.gguf Q5_K 5.07GB
Qwen2.5-7B-Instruct-Uncensored.Q5_K_M.gguf Q5_K_M 5.07GB
Qwen2.5-7B-Instruct-Uncensored.Q5_1.gguf Q5_1 5.36GB
Qwen2.5-7B-Instruct-Uncensored.Q6_K.gguf Q6_K 5.82GB
Qwen2.5-7B-Instruct-Uncensored.Q8_0.gguf Q8_0 7.54GB

Original model description:

license: gpl-3.0
datasets:

  • NobodyExistsOnTheInternet/ToxicQAFinal
  • anthracite-org/kalo-opus-instruct-22k-no-refusal
  • Orion-zhen/dpo-toxic-zh
  • unalignment/toxic-dpo-v0.2
  • Crystalcareai/Intel-DPO-Pairs-Norefusals
    language:
  • zh
  • en
    base_model:
  • Qwen/Qwen2.5-7B-Instruct
    pipeline_tag: text-generation
    tags:
  • qwen
  • uncensored

Qwen2.5-7B-Instruct-Uncensored

This model is an uncensored fine-tune version of Qwen2.5-7B-Instruct. However, I can still notice that though uncensored, the model fails to generate detailed descriptions on certain extreme scenarios, which might be associated with deletion on some pretrain datasets in Qwen's pretraining stage.

Check out my roleplay&writing enhanced model based on this model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct

Traning details

I used SFT + DPO to ensure uncensorment as well as trying to maintain original model's capabilities.

  • SFT:
    • NobodyExistsOnTheInternet/ToxicQAFinal
    • anthracite-org/kalo-opus-instruct-22k-no-refusal
  • DPO:
    • Orion-zhen/dpo-toxic-zh
    • unalignment/toxic-dpo-v0.2
    • Crystalcareai/Intel-DPO-Pairs-Norefusals

README history 1 version

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

  1. 2024-10-18uploaded readme6d2cd546 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.

Get the app Browse the catalog
Open in Abliteration