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

Tap-M/Luna-AI-Llama2-Uncensored-FP16

Tap-M Llama
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/Tap-M%2FLuna-AI-Llama2-Uncensored-FP16"
Response includes
  • classification m-uncensored
  • files 7
  • hub_downloads_all_time 33,971
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=Tap-M
All 2 models by Tap-M
 GET/models?family=llama&method=m-uncensored
Sibling llama 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
34K
132 last 30d - cooling
Likes
10
Model age
3.2y ago
created 2023-07-19
Downloads over time
Now34K→from937↑3,528%
012.4K24.9K37.3K937 on Jul 24, 202434K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Variants by this author 2 formats · 233 downloads combined

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

Metadata

License
cc-by-sa-4.0
Tags
transformers pytorch llama text-generation license:cc-by-sa-4.0 text-generation-inference endpoints_compatible region:us

Related

Other by Tap-M
Luna-AI-Llama2-Uncensored 101
Total size
12.6 GB
Files
7
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2023-07-26 19:31
Source huggingface.co/Tap-M/Luna-AI-Llama2-Uncensored-FP16 ↗

Files by quantization

Auxiliary files 7 files 12.6 GB
pytorch_model-00001-of-00002.bin 9.29 GB 91618363 download
pytorch_model-00002-of-00002.bin 3.26 GB 66580e9c download
pytorch_model.bin.index.json 26.2 KB d7f2d6c9 download
.gitattributes 1.48 KB a6344aac download
README.md 1.35 KB 0001c7ce download
config.json 633 B f0200555 download
generation_config.json 132 B 2b103309 download

README current version from Hugging Face

license: cc-by-sa-4.0

Model Description

“Luna AI Llama2 Uncensored” is a Llama2 based Chat model
fine-tuned on over 40,000 long form chat discussions
This model was fine-tuned by Tap, the creator of Luna AI.

Model Training

The fine-tuning process was performed on an 8x a100 80GB machine.
The model was trained on synthetic outputs which include multiple rounds of chats between Human & AI.

4bit GPTQ Version provided by @TheBloke - for GPU inference

GGML Version provided by @TheBloke - For CPU inference

Prompt Format

The model follows the Vicuna 1.1/ OpenChat format:

USER: I have difficulties in making friends, and I really need someone to talk to. Would you be my friend?

ASSISTANT: Of course! Friends are always here for each other. What do you like to do?

Benchmark Results
Task Version Metric Value Stderr
arc_challenge 0 acc_norm 0.5512 0.0146
hellaswag 0
mmlu 1 acc_norm 0.46521 0.036
truthfulqa_mc 1 mc2 0.4716 0.0155
Average - - 0.5114 0.0150

README history 14 versions

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

  1. 2023-07-26Update README.mdf8ff0e41.4 KB
    Loading...
  2. 2023-07-20Update README.md1fad7352.1 KB
    Loading...
  3. 2023-07-20Update README.md9aaa3792.1 KB
    Loading...
  4. 2023-07-20Update README.md2401b322.1 KB
    Loading...
  5. 2023-07-19Update README.md1fbb0bb2.1 KB
    Loading...
  6. 2023-07-19Update README.md4f5e3b02.2 KB
    Loading...
  7. 2023-07-19Update README.md9aa68042.2 KB
    Loading...
  8. 2023-07-19Update README.mde048c432.2 KB
    Loading...
  9. 2023-07-19Update README.md549d0f62.1 KB
    Loading...
  10. 2023-07-19Update README.md40284fe2.1 KB
    Loading...
  11. 2023-07-19Update README.mdbfb5f5c2 KB
    Loading...
  12. 2023-07-19Update README.md9e206c42 KB
    Loading...
  13. 2023-07-19Update README.md79bd2202 KB
    Loading...
  14. 2023-07-19Create README.md8d3286c2 KB
    Loading...

Discussions 2 threads

  1. 2025-05-21PRAdding `safetensors` variant of this modelopen1 💬#2
    Loading...
  2. 2023-07-20Sample code to launch itopen1 💬#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