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

ngxson/LoRA-llama-3-70B-Instruct-abliterated

ngxson 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/ngxson%2FLoRA-llama-3-70B-Instruct-abliterated"
Response includes
  • classification m5
  • files 4
  • benchmarks 21 entries
  • author_summary 11 models
  • readme_text full
Try next
GET/models?author=ngxson
All 11 models by ngxson
 GET/models?family=llama&method=m5
Sibling llama models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
How we label → About M5 →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
1
Descendants
1
in 1 direct fork
Model age
20mo ago
created 2025-01-22
Downloads over time
Now0→from0↑0%
00110 on Jan 22, 20250 on Oct 11Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 22, 2025 → Oct 11 · 129 snapshots · spans 627 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Arena-Battles 54380 LM-Arena
LM Arena Elo 1278.472867347656 LM-Arena
Arena-Elo-Lower 1275.1639218994935 LM-Arena
Arena-Elo-Upper 1281.7818127958183 LM-Arena
Arena-Rank 93 LM-Arena
BBH average 0.6112336230380075 OpenLLM-v2
IFEval instruct 0.919664268585132 OpenLLM-v2
IFEval-Prompt 0.8798521256931608 OpenLLM-v2
MATH lvl 5 0.0022658610271903325 OpenLLM-v2
MMLU-Pro 0.5331615691489362 OpenLLM-v2
Entertainment 3.2 UGI
Hazardous 3.5 UGI
Natural Intelligence 31.37 UGI
Political lean -18.6% UGI
Sensitive-Info 36.83 UGI
SocPol 4.3 UGI
UGI 37.89 UGI
Willingness (10) 4 UGI
W10-Adherence 3 UGI
W10-Direct 5 UGI
Writing 26.18 UGI

Genealogy 1 direct fork

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/Llama-3.3-70B-Instruct this lineage
ngxson/LoRA-llama-3-70B-Instruct-abliterated 1 fork
ggml-org/LoRA-llama-3-70B-Instruct-abliterated-F16-GGUF↓ 47

Metadata

Tags
transformers safetensors mergekit peft base_model:failspy/llama-3-70B-Instruct-abliterated base_model:finetune:failspy/llama-3-70B-Instruct-abliterated endpoints_compatible region:us

Related

Other by ngxson
DeepSeek-R1-Distill-Qwen-7B-abliterated-GGUF 851 Llama-3-Instruct-abliteration-LoRA-8B-F16-GGUF 138 LoRA-Qwen2.5-7B-Instruct-abliterated-v3 0 LoRA-Qwen2.5-14B-Instruct-abliterated-v2 0 LoRA-phi-4-abliterated 0
Same base model
huihui-ai/Llama-3.3-70B-Instruct-abliterated 17K Thaurock/Llama-3.3-70B-Instruct-abliterated-GGUF 1K Justbackup/Llama-3.3-70B-Instruct-abliterated 41 Orion-zhen/llama-3.3-70b-instruct-abliterated 22 vprilepskii/Llama-3.3-70B-Instruct-biprojected-norm-preserving-abliterated 15
Total size
809 MB
Files
4
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-01-22 08:32
Source huggingface.co/ngxson/LoRA-llama-3-70B-Instruct-abliterated ↗ Base model meta-llama/Llama-3.3-70B-Instruct ↗

Files by quantization

Auxiliary files 4 files 809 MB
adapter_model.safetensors 809 MB 8cc637b4 download
.gitattributes 1.48 KB a6344aac download
README.md 797 B 91edff7f download
adapter_config.json 785 B c08a9f85 download

README current version from Hugging Face

base_model:

  • meta-llama/Llama-3.3-70B-Instruct
  • failspy/llama-3-70B-Instruct-abliterated
    library_name: transformers
    tags:
  • mergekit
  • peft

Untitled LoRA Model (1)

This is a LoRA extracted from a language model. It was extracted using mergekit.

LoRA Details

This LoRA adapter was extracted from failspy/llama-3-70B-Instruct-abliterated and uses meta-llama/Llama-3.3-70B-Instruct as a base.

Parameters

The following command was used to extract this LoRA adapter:

mergekit-extract-lora failspy/llama-3-70B-Instruct-abliterated meta-llama/Llama-3.3-70B-Instruct OUTPUT_PATH --rank=32 --device=cpu

README history 1 version

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

  1. 2025-01-22Upload folder using huggingface_hubeb6a10b797 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.

Get the app Browse the catalog
Open in Abliteration