Cyber-Tiel-Coder-35B-A3B
35BOtheruncensored
from huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated
↓ 1M♥ 3433 repos
kldzj_gpt-oss-120b-heretic-v2
kldzj_gpt-oss-120b-heretic-v2 is a Heretic-ablated variant of kldzj/gpt-oss-120b-heretic-v2, published on Hugging Face by bartowski. It is 120B parameters, server-class deployment class and apache-2.0 licence. It is distributed across 2 repositories in GGUF format, totalling 5K downloads.
Specification
- Model name
- kldzj_gpt-oss-120b-heretic-v2
- Source repository
- bartowski/kldzj_gpt-oss-120b-heretic-v2-GGUF
- Base model
- kldzj/gpt-oss-120b-heretic-v2
- Publisher
- bartowski
- Parameters
- 120B
- VRAM required
- ~73.5 GB at Q4_K_M, 4k context (estimated) — runs on 80 GB cards
- Hardware class
- 100B+ — server-class deployment
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 21 Nov 2025
- Last updated
- 21 Nov 2025
Ablation technique
How kldzj_gpt-oss-120b-heretic-v2 was modified, and what that implies.
Heretic
Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.
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 combined with a subset of combinedallsmall.parquet from Ed Addario here”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download bartowski/kldzj_gpt-oss-120b-heretic-v2-GGUF --local-dir ./kldzj-gpt-oss-120b-heretic-v2
llama-cli -m ./kldzj-gpt-oss-120b-heretic-v2/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "bartowski/kldzj_gpt-oss-120b-heretic-v2-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve bartowski/kldzj_gpt-oss-120b-heretic-v2-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of kldzj_gpt-oss-120b-heretic-v2.
| Repository | Format | Downloads |
|---|---|---|
| bartowski/kldzj_gpt-oss-120b-heretic-v2-GGUFsource | GGUF | 5K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- kldzj_gpt-oss-120b-heretic-v2 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 kldzj/gpt-oss-120b-heretic-v2, not added by ablation — at 120B 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.
- Declared licence is apache-2.0, but the terms that bind you are kldzj/gpt-oss-120b-heretic-v2’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 kldzj_gpt-oss-120b-heretic-v2 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.