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

CONCISE/LLaMa_V2-13B-Instruct-Uncensored-HF

CONCISE 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/CONCISE%2FLLaMa_V2-13B-Instruct-Uncensored-HF"
Response includes
  • classification m-uncensored
  • files 11
  • hub_downloads_all_time 402
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=CONCISE
All 3 models by CONCISE
 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
402
27 last 30d - cooling
Likes
2
Model age
3.2y ago
created 2023-08-17

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.

ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
Downloads over time
Now407→from11↑3,600%
014929844811 on Jul 24, 2024407 on Oct 11407 on Oct 8Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Metadata

Languages
en
Tags
transformers llama text-generation nlp uncensored llama2 en dataset:ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split endpoints_compatible region:us

Related

Other by CONCISE
LLaMa_V2-13B-Instruct-Uncensored-GGML 22 LLaMa_V2-13B-Chat-Uncensored-GGML 19
Total size
24.2 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2023-08-17 15:46
Source huggingface.co/CONCISE/LLaMa_V2-13B-Instruct-Uncensored-HF ↗

Files by quantization

Auxiliary files 11 files 24.2 GB
pytorch_model-00001-of-00003.bin 9.27 GB 501e4b90 download
pytorch_model-00002-of-00003.bin 9.22 GB de657b45 download
pytorch_model-00003-of-00003.bin 5.75 GB 6c9fdc51 download
tokenizer.model 488 KB 9e556afd download
README.md 14.5 KB 42f83fd4 download
.gitattributes 1.48 KB a6344aac download
tokenizer_config.json 745 B 1e4fd8d4 download
config.json 645 B c2f8586f download
special_tokens_map.json 435 B 599f3bbf download
generation_config.json 162 B 57dbab30 download
added_tokens.json 21.0 B e41416dd download

README current version from Hugging Face

datasets:

  • ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
    language:
  • en
    library_name: transformers
    pipeline_tag: text-generation
    tags:
  • text-generation
  • nlp
  • uncensored
  • llama2

LLaMa_V2-13B-Instruct-Uncensored-HF

LLaMa.V2 13B unquantized model weights - Instruction based

Big thank you to Eric Hartford for his work aiding the creation of datasets such as:
- wizardlm_evol_instruct_V2_196k_unfiltered_merged_split
- wizard_vicuna_70k_unfiltered

Such datasets play a big role in accurately addressing model biases, without sacrificing performance



README history 1 version

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

  1. 2023-08-17Create README.md21c7bc814.5 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