← back to catalog · registered 2026-11-22 01:04

3MPER0RR/Qwen3.8-27B-3MPER0RR-abliterated-BF16-DeepSeek-V4-Flash

3MPER0RR Deepseek 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/3MPER0RR%2FQwen3.8-27B-3MPER0RR-abliterated-BF16-DeepSeek-V4-Flash"
Response includes
  • classification m1
  • files 22
  • author_summary 40 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
0
Likes
0
Model age
today
created 2026-11-21

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

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

License
apache-2.0
Tags
safetensors qwen3_5 text-generation-inference conversational deepseek distillation distill text-generation dataset:Jackrong/DeepSeek-V4-Distill-8000x base_model:3MPER0RR/Qwen3.8-27B-3MPER0RR-abliterated base_model:finetune:3MPER0RR/Qwen3.8-27B-3MPER0RR-abliterated license:apache-2.0

Related

Total size
51.0 GB
Files
22
Quantizations
1
Registered
2026-11-22 01:04
Last updated on HF
2026-11-22 00:42

Files by quantization

Auxiliary files 22 files 51.0 GB
model-00005-of-00012.safetensors 4.64 GB cc693b88 download
model-00008-of-00012.safetensors 4.63 GB 8221e45c download
model-00011-of-00012.safetensors 4.62 GB df61b733 download
model-00003-of-00012.safetensors 4.62 GB 092212d3 download
model-00009-of-00012.safetensors 4.62 GB 20f1b3b7 download
model-00010-of-00012.safetensors 4.59 GB 47d1e0f6 download
model-00007-of-00012.safetensors 4.59 GB 50108bda download
model-00006-of-00012.safetensors 4.58 GB e7cce15d download
model-00004-of-00012.safetensors 4.58 GB d06ff197 download
model-00002-of-00012.safetensors 4.51 GB 464086af download
model-00012-of-00012.safetensors 2.60 GB b78bb088 download
model-00001-of-00012.safetensors 2.37 GB 54d83c1d download
tokenizer.json 19.1 MB 06b95093 download
model.safetensors.index.json 109 KB cc8da4e6 download
License.md 10.2 KB 29fc05a0 download
chat_template.jinja 8.74 KB c0c686f9 download
tokenizer_config.json 7.02 KB 21e89e2e download
README.md 4.25 KB 23a5adb5 download
config.json 3.82 KB 69272b1e download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.19 KB 43c4343e download
generation_config.json 214 B c53835dc download

README current version from Hugging Face


license: apache-2.0
base_model:

  • 3MPER0RR/Qwen3.8-27B-3MPER0RR-abliterated
    tags:
  • text-generation-inference
  • safetensors
  • conversational
  • deepseek
  • distillation
  • distill
    datasets:
  • Jackrong/DeepSeek-V4-Distill-8000x
    pipeline_tag: text-generation

Model Details

Base model 3MPER0RR/Qwen3.8-27B-3MPER0RR-abliterated Apache 2.0
Dataset Jackrong/DeepSeek-V4-Distill-8000x MIT.
Source-questions Jackrong/GLM-5.1-Reasoning-1M-Cleaned Apache 2.0.
Teacher DeepSeek V4 Flash
Method Supervised fine-tuning (SFT) on teacher-generated Q&A (response distillation)
Reasoning format <think>...</think> (see note below)

Qwen3.8-27B – 3MPER0RR DeepSeek V4 Flash Distilled

An experimental 27B model fine-tuned using DeepSeek V4 Flash reasoning data.

Developed by 3MPER0RR, this model explores knowledge distillation and reasoning transfer from DeepSeek V4 Flash into a Qwen3.8-27B architecture.

The objective was to transfer reasoning patterns, technical problem-solving behavior and structured response generation while preserving the original model architecture.

The final checkpoint is distributed in BF16 with the LoRA adapter merged into the base model.

Model Overview

Property Value
Base model Qwen3.8-27B-3MPER0RR-abliterated
Dataset DeepSeek-V4-Distill-8000x
Fine-tuning Supervised Fine-Tuning
Distillation Response-level distillation
Adaptation LoRA
Final precision BF16
Checkpoint Merged
Reasoning Preserved

Training Methodology

The model was trained using a supervised fine-tuning pipeline based on Unsloth and TRL.

The training process used:

  • A pretrained Qwen3.8-27B checkpoint.
  • DeepSeek V4 Flash generated training responses.
  • Reasoning and final-answer supervision.
  • LoRA-based parameter adaptation.
  • BF16 training precision.
  • Final LoRA weight merging.

The training objective was to preserve structured reasoning behavior, including the separation between internal reasoning and final responses.

This project uses response-level knowledge distillation rather than direct logit-level distillation. Teacher probability distributions were not included in the dataset.

Reasoning Capabilities

The model is intended to explore improvements in:

  • Logical reasoning.
  • Technical problem solving.
  • Programming and code analysis.
  • Structured explanations.
  • Multi-step instruction following.
  • Complex question answering.

Reasoning markers such as <think> may appear in generated responses depending on the chat template and generation configuration.

Important: The presence of reasoning output does not independently demonstrate improved reasoning accuracy. Further evaluation is required.

Usage

import torch
from transformers import AutoProcessor, AutoModelForMultimodalLM

model_id = "3MPER0RR/Qwen3.8-27B-3MPER0RR-abliterated-BF16-DeepSeek-V4-Flash"

processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForMultimodalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

prompt = "Explain how ELF dynamic linking works on Linux."

messages = [
    {"role": "user", "content": [{"type": "text", "text": prompt}]}
]

inputs = processor.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device)

with torch.inference_mode():
    output = model.generate(**inputs, max_new_tokens=2048)

print(processor.decode(
    output[0][inputs["input_ids"].shape[-1]:],
    skip_special_tokens=False
))

Initial Evaluation

Initial manual inference tests demonstrated:

  • Successful model loading in BF16.
  • Successful generation.
  • Reasoning-mode behavior.
  • Structured technical responses.

README history 7 versions

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

  1. 2026-11-22 Update README.md d30180e 4.2 KB
    Loading...
  2. 2026-11-22 Update README.md 41daba9 4.2 KB
    Loading...
  3. 2026-11-22 Update README.md 48e51af 4.2 KB
    Loading...
  4. 2026-11-22 Update README.md c6dd4fd 4.2 KB
    Loading...
  5. 2026-11-21 Update README.md 330c989 4.7 KB
    Loading...
  6. 2026-11-21 Update README.md 4ede0c3 233 B
    Loading...
  7. 2026-11-21 Create README.md e396fd0 231 B
    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