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

BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored

BlossomsAI Qwen 15B
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/BlossomsAI%2FQwen2.5-Coder-14B-Instruct-Uncensored"
Response includes
  • classification m-uncensored
  • files 14
  • benchmarks 5 entries
  • hub_downloads_all_time 2,514
  • providers 1
  • author_summary 12 models
  • readme_text full
Try next
GET/models?author=BlossomsAI
All 12 models by BlossomsAI
 GET/models?family=qwen&method=m-uncensored
Sibling qwen models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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
317 last 30d - stable
Likes
7
Descendants
2
in 2 direct forks
Model age
20mo ago
created 2025-01-30
Available via
1 provider
featherless-ai
Downloads over time
Now2.6K→from21↑12,181%
09451.9K2.8K21 on Jan 29, 20252.6K on Oct 11Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 29, 2025 → Oct 11 · 128 snapshots · spans 620 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
BBH average 0.5432611233623038 OpenLLM-v2
IFEval instruct 0.7290167865707434 OpenLLM-v2
IFEval-Prompt 0.6524953789279113 OpenLLM-v2
MATH lvl 5 0.2681268882175227 OpenLLM-v2
MMLU-Pro 0.3939494680851064 OpenLLM-v2

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.

Qwen/Qwen2.5-Coder-14B-Instruct this lineage
BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored↓ 317 2 forks
mradermacher/Qwen2.5-Coder-14B-Instruct-Uncensored-GGUF↓ 1,776
natemiller1928/Qwen2.5-Coder-14B-Instruct-Uncensored-Q4_K_M-GGUF↓ 370

Variants by this author 2 formats · 3K downloads combined

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

Metadata

License
mit
Languages
en
Tags
transformers safetensors qwen2 text-generation conversational en base_model:Qwen/Qwen2.5-Coder-14B-Instruct base_model:finetune:Qwen/Qwen2.5-Coder-14B-Instruct license:mit text-generation-inference endpoints_compatible region:us

Related

Other by BlossomsAI
Qwen2.5-Coder-7B-Instruct-Uncensored-GGUF 17K Qwen2.5-Coder-14B-Instruct-Uncensored-GGUF 3K Qwen2.5-Coder-7B-Instruct-Uncensored 758 SeaLLMs-v3-1.5B-Chat-Uncensored-GGUF 354 Sailor2-8B-Chat-Uncensored-GGUF 210
Same base model
Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-14B-Instruct-abliterated-v1 9K BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored-GGUF 3K AIOpsInSpace/Qwen2.5-Coder-14B-Instruct-Uncensored-Patched 1K SSDD145/Qwen2.5-Coder-14B-Instruct-Uncensored-Patched 790 sci4ai/Qwen2.5-Coder-14B-Abliterated 525
Total size
27.5 GB
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-02-12 16:30
Source huggingface.co/BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored ↗ Base model Qwen/Qwen2.5-Coder-14B-Instruct ↗

Files by quantization

Auxiliary files 14 files 27.5 GB
model-00001-of-00006.safetensors 4.64 GB a9269de4 download
model-00003-of-00006.safetensors 4.61 GB 683781a2 download
model-00004-of-00006.safetensors 4.61 GB f5140eee download
model-00005-of-00006.safetensors 4.61 GB 64d7b10f download
model-00002-of-00006.safetensors 4.61 GB 2731801d download
model-00006-of-00006.safetensors 4.41 GB 2a027c3b download
tokenizer.json 6.71 MB 443909a6 download
vocab.json 2.65 MB 4783fe10 download
model.safetensors.index.json 46.4 KB 0e9b5353 download
tokenizer_config.json 7.13 KB acee076f download
.gitattributes 1.48 KB a6344aac download
README.md 1.30 KB 95f03efa download
config.json 733 B ffc95b35 download
generation_config.json 243 B f3e3956f download

README current version from Hugging Face

library_name: transformers
license: mit
language:

  • en
    base_model:
  • Qwen/Qwen2.5-Coder-14B-Instruct
Logo

🎯 Qwen2.5-Coder-14B-Instruct-Uncensored

An optimized version of Qwen2.5-Coder-14B-Instruct focused on removing refusal behaviors

📌 Overview

A streamlined implementation that removes refusal behaviors from Qwen/Qwen2.5-Coder-14B-Instruct, based on directional intervention techniques.

🔍 Key Features

  • Implements directional intervention for behavior modification
  • Fully quantized for resource-efficient deployment

🛠️ Implementation

Based on research findings from "Refusal in LLMs is Mediated by a Single Direction"

💫 Quantization

Pre-quantized models available in GGFU format:

🤝 Contributors

Developed with ❤️ by BlossomAI

Star ⭐️ this repo if you find it valuable!

README history 4 versions

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

  1. 2025-02-12Update README.mddc337081.3 KB
    Loading...
  2. 2025-02-12Update README.mddf8b0441.3 KB
    Loading...
  3. 2025-01-31Update README.md1ffcbe15.1 KB
    Loading...
  4. 2025-01-30Upload Qwen2ForCausalLM31f9be85.1 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.

Get the app Browse the catalog
Open in Abliteration