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

byroneverson/Mistral-Small-Instruct-2409-abliterated

byroneverson Mistral 22B
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/byroneverson%2FMistral-Small-Instruct-2409-abliterated"
Response includes
  • classification m1
  • files 25
  • benchmarks 11 entries
  • hub_downloads_all_time 160,371
  • author_summary 18 models
  • readme_text full
Try next
GET/models?author=byroneverson
All 18 models by byroneverson
 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
160K
9K last 30d - cooling
Likes
14
Descendants
5
in 5 direct forks
Model age
2.0y ago
created 2024-09-23
Downloads over time
Now164K→from6↑2,732,550%
060.1K120.2K180.4K6 on Sep 18, 2024164K on Oct 12Sep '24Jan '25May '25Sep '25JanMaySep
Sep 18, 2024 → Oct 12 · 148 snapshots · spans 754 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
Entertainment 1.9 UGI
Hazardous 3.5 UGI
Natural Intelligence 25.05 UGI
Political lean -13.5% UGI
Sensitive-Info 26.89 UGI
SocPol 3 UGI
UGI 34.6 UGI
Willingness (10) 5 UGI
W10-Adherence 5 UGI
W10-Direct 5 UGI
Writing 32.61 UGI

Genealogy 5 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.

mistralai/Mistral-Small-Instruct-2409 this lineage
byroneverson/Mistral-Small-Instruct-2409-abliterated↓ 8,556 5 forks
mradermacher/Mistral-Small-Instruct-2409-abliterated-i1-GGUF↓ 1,264
mradermacher/Mistral-Small-Instruct-2409-abliterated-GGUF↓ 737
tensorblock/Mistral-Small-Instruct-2409-abliterated-GGUF↓ 136
isetnefret/Mistral-Small-Instruct-2409-abliterated-mlx-4Bit↓ 42
byroneverson/Mistral-Small-Instruct-2409-abliterated-gguf↓ 35

Variants by this author 2 formats · 9K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
other
Languages
en
Tags
transformers safetensors mistral text-generation llm chat instruct it abliterated conversational en base_model:mistralai/Mistral-Small-Instruct-2409

Related

Other by byroneverson
Yi-1.5-9B-Chat-abliterated 9K Yi-1.5-9B-Chat-16K-abliterated 9K glm-4-9b-chat-abliterated-gguf 234 glm-4-9b-chat-abliterated 155 gemma-2-27b-it-abliterated-gguf 136
Same base model
zetasepic/Mistral-Small-Instruct-2409-abliterated 23 openerotica/Mistral-Small-Instruct-2409-abliterated-4.5bpw-exl2 21
Total size
41.4 GB
Files
25
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-09-24 10:17
Source huggingface.co/byroneverson/Mistral-Small-Instruct-2409-abliterated ↗ Base model mistralai/Mistral-Small-Instruct-2409 ↗

Files by quantization

Auxiliary files 25 files 41.5 GB
model-00005-of-00009.safetensors 4.64 GB 14adeede download
model-00008-of-00009.safetensors 4.64 GB 073226fd download
model-00002-of-00009.safetensors 4.64 GB 58f1ee9f download
model-00009-of-00009.safetensors 4.64 GB 97f83a9d download
model-00003-of-00009.safetensors 4.62 GB 4b60382a download
model-00006-of-00009.safetensors 4.62 GB bb763a1d download
model-00004-of-00009.safetensors 4.55 GB f02c4da0 download
model-00007-of-00009.safetensors 4.55 GB f60c70eb download
model-00001-of-00009.safetensors 4.55 GB 6943750c download
direction_attn.pt 1.34 MB 28de3f6c download
direction_ffn.pt 1.34 MB 132b38e6 download
direction_tok.pt 25.2 KB 03108598 download
abliterate-mistral-small-instruct-2409.ipynb 4.81 MB 78e3ce9d download
tokenizer.json 1.87 MB 4a6cc3e2 download
logo.png 835 KB df2e8804 download
tokenizer.model 574 KB 59f95e28 download
tokenizer.model.v3 574 KB 49368bb5 download
tokenizer_config.json 138 KB 828f68e1 download
model.safetensors.index.json 40.8 KB 93ef9402 download
.gitattributes 1.48 KB a6344aac download
README.md 796 B 015bea37 download
config.json 620 B 4e5beff6 download
special_tokens_map.json 437 B 72ecfeeb download
params.json 203 B 7def1e26 download
generation_config.json 116 B 5d0dd04c download

README current version from Hugging Face

base_model: mistralai/Mistral-Small-Instruct-2409
license: other
license_name: mrl
license_link: https://mistral.ai/licenses/MRL-0.1.md
pipeline_tag: text-generation
language:

  • en
    tags:
  • llm
  • mistral
  • chat
  • instruct
  • it
  • abliterated
    library_name: transformers

Mistral-Small-Instruct-2409-abliterated

Now accepting abliteration requests. If you would like to see a model abliterated, follow me and leave me a message with model link.

Check out the jupyter notebook for details of how this model was abliterated.

Logo

README history 2 versions

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

  1. 2024-09-23Update README.md69412c6796 B
    Loading...
  2. 2024-09-23initial commitebfddb094 B
    Loading...

Discussions 2 threads

  1. 2025-09-08Abliteration request for Mistral-Small-3.2-24B-Instruct-2506open2 💬#2
    Loading...
  2. 2024-10-16PRAdding Evaluation Resultsopen1 💬#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