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

venkycs/Mistral-Small-24B-Instruct-2501-Abliterated

venkycs Mistral 24B
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/venkycs%2FMistral-Small-24B-Instruct-2501-Abliterated"
Response includes
  • classification m1
  • files 21
  • benchmarks 16 entries
  • hub_downloads_all_time 1,603
  • providers 1
  • author_summary 8 models
  • readme_text full
Try next
GET/models?author=venkycs
All 8 models by venkycs
 GET/models?family=mistral&method=m1
Sibling mistral 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
2K
143 last 30d - cooling
Likes
0
Descendants
1
in 1 direct fork
Model age
20mo ago
created 2025-01-30
Available via
1 provider
featherless-ai
Downloads over time
Now1.7K→from0↑0%
06091.2K1.8K0 on Jan 29, 20251.7K on Oct 12Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 29, 2025 → Oct 12 · 129 snapshots · spans 621 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 15321 LM-Arena
LM Arena Elo 1238.5621311417763 LM-Arena
Arena-Elo-Lower 1232.9356313729072 LM-Arena
Arena-Elo-Upper 1244.1886309106455 LM-Arena
Arena-Rank 123 LM-Arena
Entertainment 2.5 UGI
Hazardous 1.8 UGI
Natural Intelligence 25.87 UGI
Political lean -17.6% UGI
Sensitive-Info 26.02 UGI
SocPol 3.4 UGI
UGI 39.01 UGI
Willingness (10) 6.5 UGI
W10-Adherence 8 UGI
W10-Direct 5 UGI
Writing 33.93 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.

mistralai/Mistral-Small-24B-Instruct-2501 this lineage
venkycs/Mistral-Small-24B-Instruct-2501-Abliterated↓ 143 1 fork
NINI26454/Mistral-Small-24B-Instruct-2501-Abliterated-GGUF↓ 428

Metadata

License
apache-2.0
Languages
en fr de es it pt zh ja ru ko
Tags
vllm safetensors mistral text-generation abliterated uncensored transformers conversational en fr de es

Related

Other by venkycs
SmolLM2-1.7B-Instruct-Abliterated 45 Llama-3.1-8B-Instruct-abliterated 19 Llama-3.1-8B-Instruct-abliterated-v2 16 llama-3.2-3b-instruct-abliterated 12 Llama-3.2-3B-Instruct-abliterated-v3 12
Same base model
huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated 2K AskVenice/venice-uncensored 342 anikaaibelarus/anika-ai-uncensored 17 Dthklok/venice-uncensored 14 aureonnewton/aureon_uncensored_v.1 13
Total size
43.9 GB
Files
21
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-12 11:10
Source huggingface.co/venkycs/Mistral-Small-24B-Instruct-2501-Abliterated ↗ Base model mistralai/Mistral-Small-24B-Instruct-2501 ↗

Files by quantization

Auxiliary files 21 files 43.9 GB
model-00004-of-00010.safetensors 4.55 GB b65fea4e download
model-00007-of-00010.safetensors 4.55 GB 62c07159 download
model-00005-of-00010.safetensors 4.45 GB e003b760 download
model-00008-of-00010.safetensors 4.45 GB 783b9ce2 download
model-00006-of-00010.safetensors 4.45 GB 8bfca933 download
model-00009-of-00010.safetensors 4.45 GB 9a4c9cf7 download
model-00003-of-00010.safetensors 4.45 GB 48a90740 download
model-00002-of-00010.safetensors 4.45 GB 80d70507 download
model-00001-of-00010.safetensors 4.45 GB dbe520ea download
model-00010-of-00010.safetensors 3.63 GB 6294c265 download
tokenizer.json 16.3 MB b76085f9 download
tekken.json 14.1 MB c4b90a96 download
tokenizer_config.json 197 KB 8fb476db download
model.safetensors.index.json 29.6 KB 69e6793e download
special_tokens_map.json 20.8 KB 642b1b50 download
.gitattributes 1.58 KB 0d4cb185 download
README.md 1.04 KB ce63386b download
SYSTEM_PROMPT.txt 997 B 71547ac2 download
config.json 649 B 2242727d download
params.json 232 B 21898cd6 download
generation_config.json 160 B 1f182124 download

README current version from Hugging Face

language:

  • en
  • fr
  • de
  • es
  • it
  • pt
  • zh
  • ja
  • ru
  • ko
    license: apache-2.0
    library_name: vllm
    inference: false
    base_model:
  • mistralai/Mistral-Small-24B-Instruct-2501
    extra_gated_description: >-
    If you want to learn more about how we process your personal data, please read
    our Privacy Policy.
    tags:
  • abliterated
  • uncensored
  • transformers

huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated

This is an uncensored version of mistralai/Mistral-Small-24B-Instruct-2501 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.

Use with ollama

You can use huihui_ai/mistral-small-abliterated directly

ollama run huihui_ai/mistral-small-abliterated

README history 2 versions

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

  1. 2025-02-25Upload folder using huggingface_hub9cf30cd1 KB
    Loading...
  2. 2025-01-30initial commit122c8aa28 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