Get the app
← back to catalog · registered 2026-08-22 13:56

matatonic/r1-1776-distill-llama-70b-abliterated-4.5bpw-exl2

matatonic Llama 70B
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/matatonic%2Fr1-1776-distill-llama-70b-abliterated-4.5bpw-exl2"
Response includes
  • classification m1
  • files 13
  • hub_downloads_all_time 446
  • author_summary 16 models
  • readme_text full
Try next
GET/models?author=matatonic
All 16 models by matatonic
 GET/models?family=llama&method=m1
Sibling llama models · same method
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
446
18 last 30d - cooling
Likes
3
Model age
19mo ago
created 2025-03-02
Downloads over time
Now453→from4↑11,225%
01663324984 on Feb 26, 2025453 on Oct 11Feb '25May '25Aug '25Nov '25FebMayAug
Feb 26, 2025 → Oct 11 · 124 snapshots · spans 592 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.

perplexity-ai/r1-1776-distill-llama-70b this lineage
matatonic/r1-1776-distill-llama-70b-abliterated-4.5bpw-exl2↓ 18

Metadata

License
mit
Tags
safetensors llama abliterated uncensored base_model:perplexity-ai/r1-1776-distill-llama-70b base_model:quantized:perplexity-ai/r1-1776-distill-llama-70b license:mit exl2 region:us

Related

Other by matatonic
GLM-4-32B-0414-abliterated-Q6_K-GGUF 69 GLM-4-32B-0414-abliterated-Q5_K_S-GGUF 46 GLM-4-32B-0414-abliterated-Q8_0-GGUF 44 DeepSeek-R1-Distill-Llama-70B-abliterated-6.5bpw-h8-exl2 33 Qwen2.5-72B-Instruct-abliterated-v2-6.5bpw-h8-exl2 26
Same base model
matatonic/r1-1776-distill-llama-70b-abliterated-6.5bpw-h8-exl2 13
Total size
38.6 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-02 17:03
Source huggingface.co/matatonic/r1-1776-distill-llama-70b-abliterated-4.5bpw-exl2 ↗ Base model perplexity-ai/r1-1776-distill-llama-70b ↗

Files by quantization

Auxiliary files 13 files 38.6 GB
output-00002-of-00004.safetensors 9.99 GB 297a9ddc download
output-00001-of-00004.safetensors 9.99 GB 47107015 download
output-00003-of-00004.safetensors 9.98 GB 948a4821 download
output-00004-of-00004.safetensors 8.64 GB 6a4c00d5 download
tokenizer.json 16.4 MB d9191504 download
measurement.json 4.26 MB 127386ad download
model.safetensors.index.json 58.9 KB 6fdd1b8d download
tokenizer_config.json 53.7 KB d901e7c5 download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.25 KB ce3857f3 download
README.md 1.23 KB c2a2a033 download
special_tokens_map.json 506 B d79576b2 download
generation_config.json 217 B 7de8125e download

README current version from Hugging Face

license: mit
base_model:

  • perplexity-ai/r1-1776-distill-llama-70b
    tags:
  • abliterated
  • uncensored

huihui-ai/r1-1776-distill-llama-70b-abliterated

This is an uncensored version of perplexity-ai/r1-1776-distill-llama-70b created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

This model refers to the https://github.com/llm-attacks/llm-attacks/tree/main/data/advbench dataset.

Use with ollama

You can use huihui_ai/perplexity-ai-r1-abliterated directly

ollama run huihui_ai/perplexity-ai-r1-abliterated

Donation

If you like it, please click 'like' and follow us for more updates.
You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.
  • bitcoin:
  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge

README history 1 version

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

  1. 2025-03-02initialf2733161.2 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.

Get the app Browse the catalog
Open in Abliteration