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

noneUsername/dolphin-2.9.2-Phi-3-Medium-abliterated-W8A8-Dynamic-Per-Token

noneUsername Phi 14B 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%2Fdolphin-2.9.2-Phi-3-Medium-abliterated-W8A8-Dynamic-Per-Token"
Response includes
  • classification m1
  • files 14
  • benchmarks 5 entries
  • hub_downloads_all_time 37
  • author_summary 17 models
  • readme_text full
Try next
GET/models?author=noneUsername
All 17 models by noneUsername
 GET/models?family=phi&method=m1
Sibling phi 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
37
12 last 30d - stable
Likes
0
Model age
23mo ago
created 2024-11-14
Downloads over time
Now42→from10↑320%
022456710 on Nov 13, 202442 on Oct 1161 on Sep 10, 2025Nov '24Feb '25May '25Aug '25Nov '25FebMayAug
Nov 13, 2024 → Oct 11 · 139 snapshots · spans 697 days

Benchmarks

Benchmark Score Source
BBH average 0.569204825528603 OpenLLM-v2
IFEval instruct 0.4772182254196642 OpenLLM-v2
IFEval-Prompt 0.34750462107208874 OpenLLM-v2
MATH lvl 5 0.005287009063444109 OpenLLM-v2
MMLU-Pro 0.45246010638297873 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.

cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated this lineage
noneUsername/dolphin-2.9.2-Phi-3-Medium-abliterated-W8A8-Dynamic-Per-Token↓ 12

Metadata

Tags
safetensors mistral base_model:dphn/dolphin-2.9.2-Phi-3-Medium-abliterated base_model:finetune:dphn/dolphin-2.9.2-Phi-3-Medium-abliterated 8-bit region:us

Related

Other by noneUsername
Qwen3-32B-abliterated-awq 3K QwQ-32B-abliterated-AWQ-INT4 26 huihui-ai-phi-4-abliterated-W8A8 20 Mistral-Small-Instruct-2409-abliterated-W8A8-Dynamic-Per-Token 17 Qwen2.5-Coder-14B-Instruct-abliterated-W8A8-Dynamic-Per-Token 17
Same base model
legraphista/dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-GGUF 1K tensorblock/dolphin-2.9.2-Phi-3-Medium-abliterated-GGUF 217 huggingkot/dolphin-2.9.2-Phi-3-Medium-abliterated-Q4_K_M-GGUF 58 itlwas/dolphin-2.9.2-Phi-3-Medium-abliterated-Q4_K_M-GGUF 31 aitorrent/dolphin-2.9.2-Phi-3-Medium-abliterated-GGUF-torrent 0
Total size
13.3 GB
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-11-14 14:03
Source huggingface.co/noneUsername/dolphin-2.9.2-Phi-3-Medium-abliterated-W8A8-Dynamic-Per-Token ↗ Base model cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated ↗

Files by quantization

Auxiliary files 14 files 13.3 GB
model-00002-of-00003.safetensors 4.65 GB 88efc271 download
model-00001-of-00003.safetensors 4.58 GB 2c131a72 download
model-00003-of-00003.safetensors 4.08 GB b7fc995f download
tokenizer.json 3.45 MB 00716372 download
tokenizer.model 488 KB 9e556afd download
model.safetensors.index.json 53.0 KB 55af438f download
tokenizer_config.json 3.32 KB 5acb2395 download
config.json 1.75 KB 6c03745c download
.gitattributes 1.48 KB a6344aac download
README.md 1.11 KB 39063086 download
special_tokens_map.json 569 B 6fdab43b download
added_tokens.json 316 B f9c61bc6 download
recipe.yaml 202 B e1e74ae4 download
generation_config.json 193 B e357d5ae download

README current version from Hugging Face

base_model:

  • cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated

vllm (pretrained=/root/autodl-tmp/dolphin-2.9.2-Phi-3-Medium-abliterated,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,gpu_memory_utilization=0.80,max_num_seqs=5), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: 5

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.836 ± 0.0235
strict-match 5 exact_match ↑ 0.760 ± 0.0271

vllm (pretrained=/root/autodl-tmp/output875,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,gpu_memory_utilization=0.80,max_num_seqs=5), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: 5

Tasks Version Filter n-shot Metric Value Stderr
gsm8k 3 flexible-extract 5 exact_match ↑ 0.856 ± 0.0222
strict-match 5 exact_match ↑ 0.776 ± 0.0264

README history 1 version

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

  1. 2024-11-14Create README.md14e1c971.1 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