Qwen2.5-Coder-14B-Instruct-Abliterated
14BQwen
from Qwen/Qwen2.5-Coder-14B-Instruct
↓ 26.7K♥ 3917 repos
Qwen2.5-Coder-14B-Instruct-Uncensored
Qwen2.5-Coder-14B-Instruct-Uncensored is a abliterated and uncensored variant of Qwen/Qwen2.5-Coder-14B-Instruct, published on Hugging Face by BlossomsAI. It is 14B parameters, 24GB VRAM class class and mit licence. It is distributed across 15 repositories in GGUF and Transformers formats, totalling 10.1K downloads.
Specification
- Model name
- Qwen2.5-Coder-14B-Instruct-Uncensored
- Source repository
- BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored
- Base model
- Qwen/Qwen2.5-Coder-14B-Instruct
- Publisher
- BlossomsAI
- Parameters
- 14B
- Hardware class
- 10B – 25B — 24GB VRAM class
- Licence
- mit
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, Transformers
- First indexed
- 30 Jan 2025
- Last updated
- 12 Feb 2025
Ablation technique
How Qwen2.5-Coder-14B-Instruct-Uncensored was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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
“A streamlined implementation that removes refusal behaviors from Qwen/Qwen2.5-Coder-14B-Instruct), based on directional intervention techniques.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored-GGUF --local-dir ./qwen2.5-coder-14b-instruct-uncensored
llama-cli -m ./qwen2.5-coder-14b-instruct-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored --trust-remote-codeDownloads and variants (14)
Every published repository of Qwen2.5-Coder-14B-Instruct-Uncensored, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen2.5-Coder-14B-Instruct-Uncensored 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.
- Capability is inherited from Qwen/Qwen2.5-Coder-14B-Instruct, not added by ablation — at 14B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- Declared licence is mit, but the terms that bind you are Qwen/Qwen2.5-Coder-14B-Instruct’s — a re-release cannot grant more than its parent.
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-Coder-14B-Instruct-Uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with BlossomsAI, and does not independently verify publisher claims. See responsible use.