← back to catalog · registered 2026-11-13 04:03

Ronin48LLC/Lamarck-Qwen3.8-27B-abliterated

Ronin48LLC 27B second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Ronin48LLC%2FLamarck-Qwen3.8-27B-abliterated"
Response includes
  • classification m1
  • files 2
  • author_summary 2 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
159
Likes
0
Model age
1w ago
created 2026-11-13
Downloads over time
Now 159 → from 0 ↑ 0%
058117175 0 on Nov 13 159 on Nov 22 Nov
Nov 13 → Nov 22 · 10 snapshots · spans 9 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

Tags
peft safetensors gguf lora qlora continued-pretraining text-generation base_model:huihui-ai/Huihui-Qwen3.8-27B-abliterated base_model:adapter:huihui-ai/Huihui-Qwen3.8-27B-abliterated region:us

Related

Total size
0 B
Files
2
Quantizations
1
Registered
2026-11-13 04:03
Last updated on HF
2026-11-15 11:03

Files by quantization

Auxiliary files 2 files 3.54 KB
README.md 2.06 KB c3e15ecf download
.gitattributes 1.48 KB a6344aac download

README current version from Hugging Face


library_name: peft
base_model: huihui-ai/Huihui-Qwen3.8-27B-abliterated
tags:

  • lora
  • qlora
  • continued-pretraining
  • text-generation

Lamarck-Qwen3.8-27B-abliterated

A LoRA adapter for
huihui-ai/Huihui-Qwen3.8-27B-abliterated,
produced by continued pretraining (QLoRA: 4-bit NF4 base, bf16 compute). Rank 16,
alpha 32, ~117M trainable parameters (~0.77% of the base). The adapter does not
modify the base weights.

This is the abliterated-base companion to
Ronin48LLC/Lamarck-Qwen3.8-27B:
the same QLoRA recipe applied to an abliterated variant of Qwen3.8-27B (the
upstream base has had refusal-related directions ablated). The adapter is
base-specific — load it on the abliterated base above, not on the pristine
Qwen/Qwen3.8-27B.

About the name

Named for Jean-Baptiste Lamarck and the inheritance of acquired characteristics.
The base model is the frozen germline; the adapter is the acquired trait layered
on top during fine-tuning, inherited by anyone who loads base + adapter.
Lamarckian inheritance, shipped as a small file.

Usage

Requires a recent transformers (the base is a Qwen3_5ForConditionalGeneration).

from transformers import Qwen3_5ForConditionalGeneration, AutoTokenizer
from peft import PeftModel

base = Qwen3_5ForConditionalGeneration.from_pretrained(
    "huihui-ai/Huihui-Qwen3.8-27B-abliterated", device_map="auto")
model = PeftModel.from_pretrained(base, "Ronin48LLC/Lamarck-Qwen3.8-27B-abliterated")
tok = AutoTokenizer.from_pretrained("huihui-ai/Huihui-Qwen3.8-27B-abliterated")

Evaluation

Pending. The adapter is measured against the unedited abliterated base, paired on
the same held-out items (MCQ accuracy plus held-out perplexity probes, with a math
control for forgetting). Results will be added here when training and evaluation
complete. These are research measurements, not a capability claim.

Limitations

A research adapter. Verify outputs; no warranty of fitness for any particular
purpose.

README history 5 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-15 Sanitize model card benchmarks to neutral probe identifiers 2fabf0d 4.5 KB
    Loading...
  2. 2026-11-15 Stage model card (adapter weights pending) b6a8f80 4.6 KB
    Loading...
  3. 2026-11-13 docs: add out-of-distribution generalization table 72bc11d 3.1 KB
    Loading...
  4. 2026-11-13 Model card with measured results 25fc05f 2.6 KB
    Loading...
  5. 2026-11-13 Stage model card (adapter weights pending) 3705cee 2.1 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration