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

Karko/toxic-sharegpt-dpo-m7b-v0.2-8k-ctx

Karko Mistral
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/Karko%2Ftoxic-sharegpt-dpo-m7b-v0.2-8k-ctx"
Response includes
  • classification unknown
  • files 11
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=mistral&method=unknown
Sibling mistral models · same method
 GET/methods/unknown
What "unknown" means · taxonomy
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)
How we label → About ? →
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
17
↑ 1,600% in 90 days
Likes
0
Model age
2.7y ago
created 2024-02-14
Downloads over time
Now51→from3↑1,600%
038761143 on Jul 24, 202451 on Oct 11104 on Sep 10, 2025Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Metadata

License
apache-2.0
Tags
transformers pytorch mistral text-generation conversational license:apache-2.0 text-generation-inference endpoints_compatible region:us
Total size
13.5 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-02-14 04:48
Source huggingface.co/Karko/toxic-sharegpt-dpo-m7b-v0.2-8k-ctx ↗

Files by quantization

Auxiliary files 11 files 13.5 GB
pytorch_model-00002-of-00003.bin 4.66 GB 9037d8ad download
pytorch_model-00001-of-00003.bin 4.60 GB c8195ee0 download
pytorch_model-00003-of-00003.bin 4.23 GB 268694f4 download
tokenizer.model 482 KB dadfd56d download
pytorch_model.bin.index.json 23.4 KB 76fccc20 download
.gitattributes 1.48 KB a6344aac download
tokenizer_config.json 1.48 KB 7d019e99 download
config.json 668 B 663c74f8 download
special_tokens_map.json 437 B 72ecfeeb download
README.md 418 B eca41aab download
generation_config.json 116 B 16923861 download

README current version from Hugging Face

license: apache-2.0

This is a finetuned version of Mistral Instruct v0.2 with Undi95's toxicsharegpt-NoWarning.jsonl. (while writing this I realize that it is not the DPO version but the NoWarning version! OOps!)

The finetuned was made at 8K context length in LoRA using axolotl.

The goal of this finetune was to check the validity of a 32K context despite a training at a way much lower context length (8k).

README history 2 versions

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

  1. 2024-02-14Update README.md24f59c4418 B
    Loading...
  2. 2024-02-14initial commit3bb063c28 B
    Loading...

Discussions 1 thread

  1. 2025-06-16PRAdding `safetensors` variant of this modelopen1 💬#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