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

letuan/Meta-Llama-3.1-8B-Instruct-abliterated-companionv4-20240927_v4c

letuan Llama 8.0B
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/letuan%2FMeta-Llama-3.1-8B-Instruct-abliterated-companionv4-20240927_v4c"
Response includes
  • classification m5
  • files 12
  • hub_downloads_all_time 40
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=letuan
All 2 models by letuan
 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 · lifetime
40
16 last 30d - stable
Likes
0
Model age
2.0y ago
created 2024-09-29
Downloads over time
Now51→from6↑750%
02958876 on Oct 2, 202451 on Oct 1179 on Sep 10, 2025Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 2, 2024 → Oct 11 · 145 snapshots · spans 739 days

Metadata

Tags
transformers safetensors llama text-generation mergekit merge conversational arxiv:2203.05482 text-generation-inference endpoints_compatible region:us

Related

Other by letuan
Qwen2.5-14B-Instruct-abliterated-v2-int4 16
Total size
15.0 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-09-29 03:30
Source huggingface.co/letuan/Meta-Llama-3.1-8B-Instruct-abliterated-companionv4-20240927_v4c ↗

Files by quantization

Auxiliary files 12 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB aee765e6 download
model-00001-of-00004.safetensors 4.61 GB b5df4f59 download
model-00003-of-00004.safetensors 4.58 GB 591093e1 download
model-00004-of-00004.safetensors 1.11 GB 6ca711a3 download
tokenizer.json 8.66 MB 777c28bc download
tokenizer_config.json 54.2 KB 38491bfe download
model.safetensors.index.json 22.3 KB 127562b3 download
.gitattributes 1.48 KB a6344aac download
README.md 1.41 KB 454d9e44 download
config.json 1010 B ae80c330 download
mergekit_config.yml 552 B 92d84752 download
special_tokens_map.json 439 B 344c8261 download

README current version from Hugging Face

base_model: []
library_name: transformers
tags:

  • mergekit
  • merge

Meta-Llama-3.1-8B-Instruct-abliterated-companionv4-20240927_v4c

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

  • /home/jovyan/llm-training-1tb/thanhtuan/models/Meta-Llama-3.1-8B-Instruct-abliterated-companionv4-20240927_v4c-e1
  • /home/jovyan/llm-training-1tb/thanhtuan/models/Meta-Llama-3.1-8B-Instruct-abliterated-companionv4-20240927_v4c-e2
  • /home/jovyan/llm-training-1tb/thanhtuan/models/Meta-Llama-3.1-8B-Instruct-abliterated-companionv4-20240927_v4c-e3

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /home/jovyan/llm-training-1tb/thanhtuan/models/Meta-Llama-3.1-8B-Instruct-abliterated-companionv4-20240927_v4c-e1
    parameters:
      weight: 1.0
  - model: /home/jovyan/llm-training-1tb/thanhtuan/models/Meta-Llama-3.1-8B-Instruct-abliterated-companionv4-20240927_v4c-e2
    parameters:
      weight: 1.0
  - model: /home/jovyan/llm-training-1tb/thanhtuan/models/Meta-Llama-3.1-8B-Instruct-abliterated-companionv4-20240927_v4c-e3
    parameters:
      weight: 1.0
merge_method: linear
dtype: bfloat16
parameters:
  normalize: true

README history 2 versions

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

  1. 2024-09-29Upload folder using huggingface_huba8056bb1.4 KB
    Loading...
  2. 2024-09-29initial commite5761ba28 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