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

Fredithefish/Guanaco-3B-Uncensored

Fredithefish Pythia 2.8B
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/Fredithefish%2FGuanaco-3B-Uncensored"
Response includes
  • classification m-uncensored
  • files 10
  • hub_downloads_all_time 55,579
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=Fredithefish
All 4 models by Fredithefish
 GET/models?family=pythia&method=m-uncensored
Sibling pythia models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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
56K
102 last 30d - cooling
Likes
3
Descendants
2
in 2 direct forks
Model age
3.1y ago
created 2023-08-23

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Fredithefish/openassistant-guanaco-unfiltered
Downloads over time
Now55.6K→from921↑5,939%
020.4K40.7K61.1K921 on Jul 24, 202455.6K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Genealogy 2 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.

Fredithefish/Guanaco-3B-Uncensored↓ 102 2 forks
tensorblock/Guanaco-3B-Uncensored-GGUF↓ 199
UKPMAN0/Guanaco-3B-Uncensored-Q5_0-GGUF↓ 30

Metadata

License
apache-2.0
Languages
en
Tags
transformers pytorch safetensors gpt_neox text-generation conversational en dataset:Fredithefish/openassistant-guanaco-unfiltered license:apache-2.0 text-generation-inference region:us

Related

Other by Fredithefish
Guanaco-3B-Uncensored-v2 180 Guanaco-13B-Uncensored 82 Guanaco-7B-Uncensored 74
Total size
10.3 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2023-08-27 21:33
Source huggingface.co/Fredithefish/Guanaco-3B-Uncensored ↗

Files by quantization

Auxiliary files 10 files 10.3 GB
pytorch_model.bin 5.17 GB a8dda97d download
model.safetensors 5.17 GB 48a4ca82 download
tokenizer.json 2.02 MB f74dfbfa download
Guanaco-Uncensored.jpg 90.9 KB bfe3ce1b download
.gitattributes 1.48 KB a6344aac download
README.md 1.27 KB 21597f12 download
config.json 744 B 70c2fb7c download
tokenizer_config.json 237 B af28df4f download
generation_config.json 111 B b789122c download
special_tokens_map.json 99.0 B 0204ed10 download

README current version from Hugging Face

license: apache-2.0
datasets:

  • Fredithefish/openassistant-guanaco-unfiltered
    language:
  • en
    library_name: transformers
    pipeline_tag: conversational
    inference: false
Alt Text

✨ Guanaco - 3B - Uncensored ✨

IMPORTANT:

This is the old model. The dataset has been updated and a newer version of this model is available here.


Guanaco-3B-Uncensored has been fine-tuned for 6 epochs on the Unfiltered Guanaco Dataset. using RedPajama-INCITE-Base-3B-v1 as the base model.

The model does not perform well with languages other than English.

Please note: This model is designed to provide responses without content filtering or censorship. It generates answers without denials.

Special thanks

I would like to thank AutoMeta for providing me with the computing power necessary to train this model.

Prompt Template

### Human: {prompt} ### Assistant:

README history 9 versions

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

  1. 2023-08-27Update README.md5eebe491.3 KB
    Loading...
  2. 2023-08-24Update README.md084a12f1 KB
    Loading...
  3. 2023-08-23Update README.mdaf90d19917 B
    Loading...
  4. 2023-08-23Update README.md618e8dd900 B
    Loading...
  5. 2023-08-23Update README.md654ae7a776 B
    Loading...
  6. 2023-08-23Update README.mdfcdeba3806 B
    Loading...
  7. 2023-08-23Update README.md2f4260d711 B
    Loading...
  8. 2023-08-23Update README.md09075dc500 B
    Loading...
  9. 2023-08-23Create README.md324418c166 B
    Loading...

Discussions 4 threads

  1. 2024-02-16PRAdd default chat template to tokenizer_config.jsonopen1 💬#4
    Loading...
  2. 2024-02-16PRAdd default chat template to tokenizer_config.jsonclosed1 💬#3
    Loading...
  3. 2023-11-17PRAdding Evaluation Resultsopen1 💬#2
    Loading...
  4. 2023-08-23PRAdding `safetensors` variant of this modelmerged1 💬#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