Qwen3.8-Flash-Next-Uncensored
Qwenuncensoredgated
from Qwen/Qwen3.8-Flash-Next
↓ 247.3K♥ 24317 repos
Qwen2.5-14B_Uncensored_Instruct
Qwen2.5-14B_Uncensored_Instruct is a refusal-ablated open-weight language model, published on Hugging Face by bartowski. It is apache-2.0 licence. It is distributed across 5 repositories in GGUF and GGUF (imatrix) formats, totalling 38.4K downloads.
Specification
- Model name
- Qwen2.5-14B_Uncensored_Instruct
- Source repository
- bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF
- Base model
- Not declared
- Publisher
- bartowski
- Parameters
- Not determinable from name
- Hardware class
- Unknown
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, GGUF (imatrix)
- First indexed
- 22 Sept 2024
- Last updated
- 23 Sept 2024
Ablation technique
How Qwen2.5-14B_Uncensored_Instruct was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“All quants made using imatrix option with dataset from here”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF --local-dir ./qwen2.5-14b-uncensored-instruct
llama-cli -m ./qwen2.5-14b-uncensored-instruct/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUF --trust-remote-codeDownloads and variants (4)
Every published repository of Qwen2.5-14B_Uncensored_Instruct, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| bartowski/Qwen2.5-14B_Uncensored_Instruct-GGUFsource | GGUF | 36.8K |
| mradermacher/Qwen2.5-14B_Uncensored_Instruct-i1-GGUF | GGUF (imatrix) | 932 |
| mradermacher/Qwen2.5-14B_Uncensored_Instruct-GGUF | GGUF | 546 |
| YorkieOH10/Qwen2.5-14B_Uncensored_Instruct-Q4_K_M-GGUF | GGUF | 166 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen2.5-14B_Uncensored_Instruct will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for Qwen2.5-14B_Uncensored_Instruct is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with bartowski, and does not independently verify publisher claims. See responsible use.