Sage-A1.5-Heretic-Abliterated-Uncensored
Otherheretic
from InternScience/Sage-A1.5
↓ 14.1K♥ 64 repos
Sage-A1.5-abliterated-MTP-FIT
Sage-A1.5-abliterated-MTP-FIT is a refusal-ablated variant of InternScience/Sage-A1.5, published on Hugging Face by SC117. It is apache-2.0 licence. It is distributed across 2 repositories in GGUF format, totalling 6.3K downloads.
Specification
- Model name
- Sage-A1.5-abliterated-MTP-FIT
- Source repository
- SC117/Sage-A1.5-abliterated-MTP-FIT-GGUF
- Base model
- InternScience/Sage-A1.5
- Publisher
- SC117
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- 512K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 30 Oct 2026
- Last updated
- 31 Oct 2026
Ablation technique
How Sage-A1.5-abliterated-MTP-FIT 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
“Five fidelity tiers of a 35B MoE agentic model — each one the smallest GGUF that provably meets its KL gate, re-measured on its own shipped bytes.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download SC117/Sage-A1.5-abliterated-MTP-FIT-GGUF --local-dir ./sage-a1.5-abliterated-mtp-fit
llama-cli -m ./sage-a1.5-abliterated-mtp-fit/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "SC117/Sage-A1.5-abliterated-MTP-FIT-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve SC117/Sage-A1.5-abliterated-MTP-FIT-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of Sage-A1.5-abliterated-MTP-FIT.
| Repository | Format | Downloads |
|---|---|---|
| SC117/Sage-A1.5-abliterated-MTP-FIT-GGUFsource | GGUF | 6.3K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Sage-A1.5-abliterated-MTP-FIT 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.
- Declared licence is apache-2.0, but the terms that bind you are InternScience/Sage-A1.5’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 Sage-A1.5-abliterated-MTP-FIT is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with SC117, and does not independently verify publisher claims. See responsible use.