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

chplushsieh/Meta-Llama-3-8B-Instruct-abliterated-v3-GPTQ-4bit

chplushsieh Llama 7.0B
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/chplushsieh%2FMeta-Llama-3-8B-Instruct-abliterated-v3-GPTQ-4bit"
Response includes
  • classification m1
  • files 10
  • hub_downloads_all_time 663
  • author_summary 1 models
  • readme_text full
Try next
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
663
17 last 30d - cooling
Likes
0
Model age
2.4y ago
created 2024-06-03
Downloads over time
Now667→from20↑3,235%
024548973420 on Jul 24, 2024667 on Oct 11667 on Oct 9Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Metadata

License
llama3
Tags
transformers safetensors llama text-generation conversational license:llama3 text-generation-inference endpoints_compatible 4-bit gptq region:us
Total size
5.34 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-06-05 07:34
Source huggingface.co/chplushsieh/Meta-Llama-3-8B-Instruct-abliterated-v3-GPTQ-4bit ↗

Files by quantization

Auxiliary files 10 files 5.35 GB
model-00001-of-00002.safetensors 4.36 GB cdd4063c download
model-00002-of-00002.safetensors 1002 MB 8005050c download
tokenizer.json 8.66 MB b197f72e download
model.safetensors.index.json 76.6 KB 9f295f1a download
tokenizer_config.json 49.8 KB 1bfd1146 download
.gitattributes 1.48 KB a6344aac download
config.json 1000 B 1b360df4 download
README.md 330 B 0bf31898 download
special_tokens_map.json 296 B 02ee80b6 download
generation_config.json 194 B 6bc1f7e8 download

README current version from Hugging Face

license: llama3
library_name: transformers

Description

This is a 4-bit GPTQ quantized model of failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
It is quantized with wikitext2 dataset.
Its file size is 5.73 GB, and can fit into a 8GB VRAM GPU.

README history 5 versions

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

  1. 2024-06-05Update README.md0491f65330 B
    Loading...
  2. 2024-06-03Update README.md987fe6c331 B
    Loading...
  3. 2024-06-03Upload tokenizercdb922b334 B
    Loading...
  4. 2024-06-03Wrote READMEd02d145334 B
    Loading...
  5. 2024-06-03Upload LlamaForCausalLMd32f73a5.1 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.

Get the app Browse the catalog
Open in Abliteration