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

noneUsername/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-W8A8-Dynamic-Per-Token

noneUsername Qwen 13B second-order
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/noneUsername%2FJosiefied-Qwen2.5-14B-Instruct-abliterated-v4-W8A8-Dynamic-Per-Token"
Response includes
  • classification m1
  • files 16
  • benchmarks 5 entries
  • hub_downloads_all_time 33
  • author_summary 17 models
  • readme_text full
Try next
GET/models?author=noneUsername
All 17 models by noneUsername
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
33
12 last 30d - stable
Likes
0
Model age
23mo ago
created 2024-11-08
Downloads over time
Now35→from4↑775%
03060904 on Nov 6, 202435 on Oct 1282 on Jan 14Nov '24Feb '25May '25Aug '25Nov '25FebMayAug
Nov 6, 2024 → Oct 12 · 141 snapshots · spans 705 days

Benchmarks

Benchmark Score Source
BBH average 0.5680373589311195 OpenLLM-v2
IFEval instruct 0.8561151079136691 OpenLLM-v2
IFEval-Prompt 0.8022181146025879 OpenLLM-v2
MATH lvl 5 0 OpenLLM-v2
MMLU-Pro 0.5018284574468085 OpenLLM-v2

Genealogy 0 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.

Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4↓ 252 this lineage
noneUsername/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-W8A8-Dynamic-Per-Token↓ 12

Metadata

Tags
safetensors qwen2 base_model:Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4 base_model:quantized:Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4 8-bit compressed-tensors region:us

Related

Other by noneUsername
Qwen3-32B-abliterated-awq 3K QwQ-32B-abliterated-AWQ-INT4 24 huihui-ai-phi-4-abliterated-W8A8 20 Qwen2.5-Coder-14B-Instruct-abliterated-W8A8-Dynamic-Per-Token 17 Seed-Coder-8B-Instruct-abliterated-W8A8 17
Same base model
Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-gguf 2K mradermacher/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-i1-GGUF 1K mradermacher/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-GGUF 402 mlx-community/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-8-bit 140 mlx-community/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-4-bit 130
Total size
15.2 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-11-11 14:08
Source huggingface.co/noneUsername/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4-W8A8-Dynamic-Per-Token ↗ Base model Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4 →

Files by quantization

Auxiliary files 16 files 15.2 GB
model-00001-of-00004.safetensors 4.65 GB 10f1e5df download
model-00002-of-00004.safetensors 4.62 GB 9489a14b download
model-00003-of-00004.safetensors 4.49 GB 55485b36 download
model-00004-of-00004.safetensors 1.45 GB 961282a7 download
tokenizer.json 10.9 MB 63a2951d download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 75.0 KB 5ba6d9c4 download
tokenizer_config.json 8.73 KB dbafeefb download
config.json 1.80 KB 6b5b37ee download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.07 KB 513a29be download
special_tokens_map.json 613 B ac23c0aa download
added_tokens.json 605 B 482ced46 download
generation_config.json 243 B f237e177 download
recipe.yaml 201 B de609f4e download

README current version from Hugging Face

base_model:

  • Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4

vllm (pretrained=/root/autodl-tmp/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.472 ± 0.0316
strict-match 5 exact_match ↑ 0.856 ± 0.0222

vllm (pretrained=/root/autodl-tmp/output1,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.544 ± 0.0316
strict-match 5 exact_match ↑ 0.856 ± 0.0222

README history 2 versions

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

  1. 2024-11-11Update README.mdbff8b341.1 KB
    Loading...
  2. 2024-11-08Create README.md7a20f17608 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