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

win10/Mistral-Nemo-abliterated-Nemo-Pro-v2

win10 Mistral 12B
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/win10%2FMistral-Nemo-abliterated-Nemo-Pro-v2"
Response includes
  • classification m5
  • files 13
  • hub_downloads_all_time 782
  • providers 1
  • author_summary 13 models
  • readme_text full
Try next
GET/models?author=win10
All 13 models by win10
 GET/models?family=mistral&method=m5
Sibling mistral models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
How we label → About M5 →
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
782
78 last 30d - cooling
Likes
1
Descendants
3
in 3 direct forks
Model age
22mo ago
created 2024-11-25
Available via
1 provider
featherless-ai
Downloads over time
Now803→from0↑0%
02945898830 on Nov 20, 2024803 on Oct 12Nov '24Feb '25May '25Aug '25Nov '25FebMayAug
Nov 20, 2024 → Oct 12 · 139 snapshots · spans 691 days

Genealogy 3 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.

shuttleai/shuttle-2.5-mini this lineage
win10/Mistral-Nemo-abliterated-Nemo-Pro-v2↓ 78 3 forks
mradermacher/Mistral-Nemo-abliterated-Nemo-Pro-v2-i1-GGUF↓ 1,065
mradermacher/Mistral-Nemo-abliterated-Nemo-Pro-v2-GGUF↓ 281
win10/Mistral-Nemo-abliterated-Nemo-Pro-v2-Q8_0-GGUF↓ 53

Metadata

Tags
transformers safetensors mistral text-generation mergekit merge conversational arxiv:2306.01708 base_model:dphn/dolphin-2.9.3-mistral-nemo-12b base_model:merge:dphn/dolphin-2.9.3-mistral-nemo-12b base_model:natong19/Mistral-Nemo-Instruct-2407-abliterated base_model:merge:natong19/Mistral-Nemo-Instruct-2407-abliterated

Related

Other by win10
GPT-OSS-26B-abliterated-Preview-Q8_0-GGUF 63 Mistral-Nemo-abliterated-Nemo-Pro-v2-Q8_0-GGUF 53 GPT-OSS-26B-abliterated-Preview-Q4_K_M-GGUF 45 GPT-OSS-26B-abliterated-Preview 42 internlm2_5-20b-chat-abliterated-Q6_K-GGUF 30
Total size
22.8 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-11-25 07:42
Source huggingface.co/win10/Mistral-Nemo-abliterated-Nemo-Pro-v2 ↗ Base model shuttleai/shuttle-2.5-mini ↗

Files by quantization

Auxiliary files 13 files 22.8 GB
model-00003-of-00005.safetensors 4.57 GB c5c5d5b9 download
model-00002-of-00005.safetensors 4.57 GB d5e850be download
model-00004-of-00005.safetensors 4.57 GB 41df5122 download
model-00005-of-00005.safetensors 4.57 GB 12c48766 download
model-00001-of-00005.safetensors 4.53 GB f591d99f download
tokenizer.json 16.3 MB b0240ce5 download
tokenizer_config.json 177 KB fe167a9b download
model.safetensors.index.json 27.8 KB abcf667b download
README.md 1.75 KB 20aa5c2e download
.gitattributes 1.53 KB 52373fe2 download
mergekit_config.yml 819 B f51f48c0 download
config.json 741 B bde3ff01 download
special_tokens_map.json 552 B a782b2f1 download

README current version from Hugging Face

base_model:

  • shuttleai/shuttle-2.5-mini
  • cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
  • natong19/Mistral-Nemo-Instruct-2407-abliterated
    library_name: transformers
    tags:
  • mergekit
  • merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using natong19/Mistral-Nemo-Instruct-2407-abliterated as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: shuttleai/shuttle-2.5-mini
    parameters:
      density: 1
      weight: 1 
      
  - model: cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
    parameters:
      density: 1
      weight: 1 
      
  - model: natong19/Mistral-Nemo-Instruct-2407-abliterated
    parameters:
      density: 1
      weight: 1 
        
  - model: shuttleai/shuttle-2.5-mini
    parameters:
      density: 1
      weight: 1 
      
  - model: cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
    parameters:
      density: 1
      weight: 1 
      
  - model: natong19/Mistral-Nemo-Instruct-2407-abliterated
    parameters:
      density: 1
      weight: 1 
      
merge_method: ties
base_model: natong19/Mistral-Nemo-Instruct-2407-abliterated
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16

README history 1 version

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

  1. 2024-11-25Upload folder using huggingface_hub9c609da1.7 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