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

IlyaGusev/saiga_llama3_8b_sft_m11_d5_abliterated_kto_m5_d3

IlyaGusev Llama 8.0B
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/IlyaGusev%2Fsaiga_llama3_8b_sft_m11_d5_abliterated_kto_m5_d3"
Response includes
  • classification m1
  • files 11
  • hub_downloads_all_time 276
  • author_summary 16 models
  • readme_text full
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
276
14 last 30d - cooling
Likes
1
Model age
2.3y ago
created 2024-06-11
Downloads over time
Now280→from13↑2,054%
010320530813 on Jul 24, 2024280 on Oct 11280 on Oct 9Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Metadata

Tags
transformers safetensors llama text-generation conversational text-generation-inference endpoints_compatible region:us

Related

Total size
15.0 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-06-11 20:23

Files by quantization

Auxiliary files 11 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB 83ce2d3b download
model-00001-of-00004.safetensors 4.63 GB bac19e69 download
model-00003-of-00004.safetensors 4.58 GB d1fed9b4 download
model-00004-of-00004.safetensors 1.09 GB fce7ea9a download
tokenizer.json 8.66 MB a3c73537 download
tokenizer_config.json 49.9 KB 45f19ec8 download
model.safetensors.index.json 23.4 KB 0fd8120f download
.gitattributes 1.80 KB 84e623b8 download
config.json 738 B e11bcdf4 download
generation_config.json 194 B 72d4581e download
special_tokens_map.json 104 B 01f00d74 download

README

The author did not publish a README.

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.

Open in Abliteration