library_name: transformers
tags:
- Distill
base_model: - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
DeepSeek-R1-Distill-Qwen-1.5B-Abliterated-dpo
dpo trained- to recoupe some of abliteration loss
stepenZEN/DeepSeek-R1-Distill-Qwen-1.5B-Abliterated-dpo
Your rig
guess connected
? Why do I need an app?
The browser can't see your hardware
For privacy reasons a browser tells us at most "≥ 8 GB RAM, 8 cores" - same reading whether you have 8 GB or 128 GB. It has no idea how much RAM is free right now, which apps are open, or whether you have a GPU.
The Abliteration app is integrated with your machine
It reads your exact RAM, GPU model and VRAM, free memory right now, and picks the sharpest quant that still fits. Every model page lights up precisely for your rig.
And you can chat with any model, right now
The app is a full local runtime - no API keys, no subscription, everything runs on your machine. Click any model on this site and start a conversation in seconds.
Get the free 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/stepenZEN%2FDeepSeek-R1-Distill-Qwen-1.5B-Abliterated-dpo" Response includes
- classification m4
- files 8
- benchmarks 5 entries
- hub_downloads_all_time 967
- author_summary 7 models
- readme_text full
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
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
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
967
49 last 30d
- cooling
Likes
3
Descendants
3
in 3 direct forks
Model age
20mo ago
created 2025-01-24
Downloads over time
Jan 22, 2025 → Oct 11 · 129 snapshots · spans 627 days
Benchmarks
Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
| Benchmark | Score | Source |
|---|---|---|
| BBH average | 0.31521598132053447 | OpenLLM-v2 |
| IFEval instruct | 0.4172661870503597 | OpenLLM-v2 |
| IFEval-Prompt | 0.2754158964879852 | OpenLLM-v2 |
| MATH lvl 5 | 0 | OpenLLM-v2 |
| MMLU-Pro | 0.11868351063829788 | OpenLLM-v2 |
Genealogy
Full fork graph →This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B this lineage
Metadata
Related
Source huggingface.co/stepenZEN/DeepSeek-R1-Distill-Qwen-1.5B-Abliterated-dpo ↗ Base model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B ↗
Files by quantization
Auxiliary files 8 files 3.32 GB
| model.safetensors | 3.31 GB | 2f33ab49 | download |
| tokenizer.json | 10.9 MB | a4256422 | download |
| tokenizer_config.json | 6.70 KB | 12a18d88 | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| config.json | 766 B | cc8906ca | download |
| special_tokens_map.json | 485 B | 1d385d62 | download |
| README.md | 206 B | 3a7d6024 | download |
| generation_config.json | 181 B | b6f949be | download |
README
README history
The author's README evolved over time. Click a version to see its content at that point.
2025-01-24Update README.md
Loading...2025-01-24Upload Qwen2ForCausalLM
Loading...
Discussions
2025-02-13DPO Training Dataset?
Loading...2025-01-29bad performance
Loading...2025-01-24GGUF?
Loading...