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

TroyDoesAI/Unaligned-Llama-13B

TroyDoesAI Llama 13B
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/TroyDoesAI%2FUnaligned-Llama-13B"
Response includes
  • classification unknown
  • files 14
  • author_summary 8 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
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 · 30-day
11
↑ 150% in 90 days
Likes
0
Descendants
2
in 2 direct forks
Model age
2.1y ago
created 2024-09-13
Downloads over time
Now35→from14↑150%
023456814 on Sep 11, 202435 on Oct 1162 on Sep 10, 2025Sep '24Jan '25May '25Sep '25JanMaySep
Sep 11, 2024 → Oct 11 · 148 snapshots · spans 760 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.

Metadata

Tags
safetensors llama license:artistic-2.0 region:us

Related

Total size
24.2 GB
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-09-13 23:16

Files by quantization

Auxiliary files 14 files 24.2 GB
model-00001-of-00006.safetensors 4.65 GB 0bb48cb6 download
model-00002-of-00006.safetensors 4.63 GB 30ac6fce download
model-00004-of-00006.safetensors 4.59 GB 00f002a3 download
model-00005-of-00006.safetensors 4.59 GB a941c5b6 download
model-00003-of-00006.safetensors 4.59 GB 5d679165 download
model-00006-of-00006.safetensors 1.18 GB ed977ed2 download
tokenizer.json 1.76 MB 0f836501 download
tokenizer.model 488 KB 9e556afd download
model.safetensors.index.json 27.8 KB ae6aaed5 download
.gitattributes 1.48 KB a6344aac download
tokenizer_config.json 1.01 KB 8adea679 download
README.md 850 B b994b61c download
config.json 741 B 27f4fe26 download
special_tokens_map.json 578 B ed4f6793 download

README current version from Hugging Face


license: artistic-2.0

When your tired of the slop, it might be nice to visit an old friend, LLama 2 13B, back when the outputs just felt more magical.
Back when it wasnt all about benchmarks.

Model was tuned using Two Formats:

Use This Template for Ollama Model File

TEMPLATE """
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

{{ if .System }}### Instruction:
{{ .System }}{{ end }}

{{ if .Prompt }}### Input:
{{ .Prompt }}{{ end }}

### Response:
"""

Also Context-Obedient Template:

TEMPLATE """
BEGININPUT
BEGINCONTEXT
ENDCONTEXT
{{ if .System }}<|system|>:{{ .System }}{{ end }}
ENDINPUT
BEGININSTRUCTION
{{ if .Prompt }}{{ .Prompt }}{{ end }}
ENDINSTRUCTION
### Contextual Response
{{ .Response }}
"""

README history 3 versions

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

  1. 2024-09-13Update README.md3d553f1850 B
    Loading...
  2. 2024-09-13Update README.md96a26c5675 B
    Loading...
  3. 2024-09-13initial commitd04f36330 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.

Open in Abliteration