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

reissbaker/llama-3.1-70b-abliterated-lora

reissbaker 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/reissbaker%2Fllama-3.1-70b-abliterated-lora"
Response includes
  • classification m1
  • files 5
  • hub_downloads_all_time 339,130
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=reissbaker
All 2 models by reissbaker
 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
339K
43 last 30d - cooling
Likes
4
Model age
20mo ago
created 2025-01-31
Downloads over time
Now339.1K→from0↑0%
0124.4K248.7K373.1K0 on Jan 29, 2025339.1K on Oct 11339.1K on Oct 10Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 29, 2025 → Oct 11 · 128 snapshots · spans 620 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.

meta-llama/Meta-Llama-3.1-70B-Instruct this lineage
reissbaker/llama-3.1-70b-abliterated-lora↓ 43

Metadata

Tags
peft safetensors base_model:meta-llama/Llama-3.1-70B-Instruct base_model:adapter:meta-llama/Llama-3.1-70B-Instruct region:us

Related

Other by reissbaker
llama-3.1-8b-abliterated-lora 283
Same base model
Guilherme34/Meta-Llama-3.1-70B-Chat-Uncensored 11
Total size
1.54 GB
Files
5
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-02-06 06:05
Source huggingface.co/reissbaker/llama-3.1-70b-abliterated-lora ↗ Base model meta-llama/Meta-Llama-3.1-70B-Instruct ↗

Files by quantization

Auxiliary files 5 files 1.54 GB
adapter_model.safetensors 1.54 GB d1c4587f download
unfat-config.py 1.63 KB a110f9b2 download
.gitattributes 1.48 KB a6344aac download
README.md 1.33 KB 0bcc3b3a download
adapter_config.json 808 B e64db059 download

README current version from Hugging Face

base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
library_name: peft

Model Card for Model ID

This LoRA adapter was extracted from
mlabonne/Meta-Llama-3.1-70B-Instruct-lorablated
and uses
meta-llama/Llama-3.1-70B-Instruct
as a base.

Model Details

The model was extracted by running
mlabonne/harmful_behaviors
and the user prompts (but not assistant responses or system messages) from
Guilherme34/uncensor
through the original abliterated model to generate a dataset of
prompt/completion pairs, and was trained for 2 epochs on a 8xA100s with Axolotl
using FSDP. Since the original abliterated model isn't perfect at avoiding
refusals, the dataset was cleaned to remove the few refusals generated prior to
training.

Model Description

  • Developed by: @reissbaker
  • Funded by: Synthetic Lab
  • License: Apache 2.0
  • Finetuned from model: Llama 3.1 70B Instruct

How to Get Started with the Model

Run the model with one click on glhf.chat.

Training Hyperparameters

  • BF16 mixed-precision
  • 4e-4 LR
  • Linear LR schedule
  • Fused AdamW optimizer

README history 1 version

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

  1. 2025-02-05Add README97e01d41.3 KB
    Loading...

Discussions 1 thread

  1. 2025-02-13Tool Callingopen3 💬#1
    Loading...

Continue on Hugging Face →

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