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

RichardErkhov/Fredithefish_-_Guanaco-3B-Uncensored-v2-8bits

RichardErkhov Pythia 2.5B
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/RichardErkhov%2FFredithefish_-_Guanaco-3B-Uncensored-v2-8bits"
Response includes
  • classification m-uncensored
  • files 8
  • hub_downloads_all_time 83
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=RichardErkhov
All 257 models by RichardErkhov
 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
83
5 last 30d - cooling
Likes
0
Model age
2.0y ago
created 2024-10-06
Downloads over time
Now86→from10↑760%
032639510 on Oct 2, 202486 on Oct 11Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 2, 2024 → Oct 11 · 145 snapshots · spans 739 days

Metadata

Tags
safetensors gpt_neox 8-bit bitsandbytes region:us

Related

Other by RichardErkhov
byroneverson_-_gemma-2-27b-it-abliterated-gguf 2K huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-gguf 2K failspy_-_Codestral-22B-v0.1-abliterated-v3-gguf 2K Rupesh2_-_Llama-3.1-8B-Uncensored-gguf 2K huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf 2K
Total size
2.83 GB
Files
8
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-10-06 13:30
Source huggingface.co/RichardErkhov/Fredithefish_-_Guanaco-3B-Uncensored-v2-8bits ↗

Files by quantization

Auxiliary files 8 files 2.83 GB
model.safetensors 2.83 GB c39f50dd download
tokenizer.json 2.02 MB eb39a3d9 download
tokenizer_config.json 4.69 KB 63a234c2 download
README.md 1.57 KB e704180e download
.gitattributes 1.48 KB a6344aac download
config.json 1.20 KB ed563d20 download
special_tokens_map.json 441 B 7fb88369 download
generation_config.json 111 B 817b5a2e download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Guanaco-3B-Uncensored-v2 - bnb 8bits

Original model description:

license: apache-2.0
datasets:

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

✨ Guanaco - 3B - Uncensored ✨

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:

Changes

This is the second version of the 3B parameter Guanaco uncensored model.
The model has been fine-tuned on the V2 of the Guanaco unfiltered dataset.

README history 1 version

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

  1. 2024-10-06uploaded readme942bee61.6 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