Cyber-Tiel-Coder-35B-A3B
35BOtheruncensored
from huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated
↓ 1M♥ 3433 repos
WizardLM-1.0-Uncensored-CodeLlama-34b
WizardLM-1.0-Uncensored-CodeLlama-34b is a abliterated and uncensored variant of QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b, published on Hugging Face by QuixiAI. It is 34B parameters, 48GB VRAM class class and llama2 licence. It is distributed across 7 repositories in Transformers, GGUF, GPTQ and AWQ formats, totalling 5.8K downloads.
Specification
- Model name
- WizardLM-1.0-Uncensored-CodeLlama-34b
- Source repository
- QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b
- Publisher
- QuixiAI
- Parameters
- 34B
- VRAM required
- ~21.5 GB at Q4_K_M, 4k context (estimated) — runs on 24 GB cards
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- llama2
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers, GGUF, GPTQ, AWQ, GGUF (imatrix)
- First indexed
- 29 Aug 2023
- Last updated
- 31 Jul 2025
Ablation technique
How WizardLM-1.0-Uncensored-CodeLlama-34b 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
“This model is trained on top of CodeLlama-34b, which gives it some very good coding abilities.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GGUF --local-dir ./wizardlm-1.0-uncensored-codellama-34b
llama-cli -m ./wizardlm-1.0-uncensored-codellama-34b/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b --trust-remote-codeDownloads and variants (6)
Every published repository of WizardLM-1.0-Uncensored-CodeLlama-34b, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GGUF | GGUF | 4.1K |
| mradermacher/WizardLM-1.0-Uncensored-CodeLlama-34b-i1-GGUF | GGUF (imatrix) | 994 |
| mradermacher/WizardLM-1.0-Uncensored-CodeLlama-34b-GGUF | GGUF | 492 |
| TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-GPTQ | GPTQ | 70 |
| QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34bsource | Transformers | 58 |
| TheBloke/WizardLM-1.0-Uncensored-CodeLlama-34B-AWQ | AWQ | 39 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- WizardLM-1.0-Uncensored-CodeLlama-34b 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 QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b, not added by ablation — at 34B 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 llama2, but the terms that bind you are QuixiAI/WizardLM-1.0-Uncensored-CodeLlama-34b’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 WizardLM-1.0-Uncensored-CodeLlama-34b is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with QuixiAI, and does not independently verify publisher claims. See responsible use.