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

adamo1139/yi-34b-200k-xlctx-aezakmi-raw-toxic-dpo-sft-orpo-lora-0205

adamo1139 Yi 34B
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/adamo1139%2Fyi-34b-200k-xlctx-aezakmi-raw-toxic-dpo-sft-orpo-lora-0205"
Response includes
  • classification m4
  • files 3
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=yi&method=m4
Sibling yi models · same method
 GET/methods/m4
What "m4" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M4
Primary method

Abliterate + heal

Applied on top of direct removal inherited from the base model.
Confidence
LOW
Inherited from base model
M1 Direct removal →
Why this label 2 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'healed'/'orpo'/'dpo' in name suggests heal step after abliteration
  • M4 = abliterate + heal pipeline
How we label → About M4 →
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
0
Likes
0
Model age
2.4y ago
created 2024-05-02

Training datasets

1 of 3 in /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.

adamo1139/toxic-dpo-natural-v5 heal adamo1139/AEZAKMI_v3-7 adamo1139/rawrr_v2-2_stage1
Downloads over time
Now0→from0↑0%
00110 on Jul 24, 20240 on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Metadata

License
apache-2.0
Tags
safetensors dataset:adamo1139/toxic-dpo-natural-v5 dataset:adamo1139/AEZAKMI_v3-7 dataset:adamo1139/rawrr_v2-2_stage1 license:apache-2.0 region:us
Total size
0 B
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-05-27 21:37
Source huggingface.co/adamo1139/yi-34b-200k-xlctx-aezakmi-raw-toxic-dpo-sft-orpo-lora-0205 ↗

Files by quantization

Auxiliary files 3 files 2.02 KB
.gitattributes 1.48 KB a6344aac download
README.md 547 B 72680244 download
LICENSE 0 B e69de29b download

README current version from Hugging Face

license: apache-2.0
datasets:

  • adamo1139/toxic-dpo-natural-v5
  • adamo1139/AEZAKMI_v3-7
  • adamo1139/rawrr_v2-2_stage1

Collection of LoRA files for my finetune. First, there was DPO on adamo1139/rawrr_v2-2_stage1 for 1 epoch. Then, SFT training on adamo1139/AEZAKMI_v3-7 for 0.5 epochs. Then, ORPO training on adamo1139/toxic-dpo-natural-v5 for 1 epoch.
I like the resulting model so far, it does feel very natural and uncensored, ORPO training really turned out nicely and was also super quick! Exciting for models in the future for sure!

README history 4 versions

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

  1. 2024-05-27Update README.md68fec84547 B
    Loading...
  2. 2024-05-03Update README.md558bfb4589 B
    Loading...
  3. 2024-05-03Update README.md3786874491 B
    Loading...
  4. 2024-05-02initial commit81d977d70 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.

Get the app Browse the catalog
Open in Abliteration