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

IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_kto_m1_d2

IlyaGusev Llama 71B
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_70b_sft_m1_d5_abliterated_kto_m1_d2"
Response includes
  • classification m1
  • files 37
  • hub_downloads_all_time 274
  • 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
274
12 last 30d - cooling
Likes
0
Model age
2.3y ago
created 2024-06-17
Downloads over time
Now278→from33↑742%
010220430633 on Jul 24, 2024278 on Oct 11278 on Oct 10Jul '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
131 GB
Files
37
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-06-17 00:55

Files by quantization

Auxiliary files 37 files 131 GB
model-00008-of-00030.safetensors 4.66 GB 0ae96488 download
model-00013-of-00030.safetensors 4.66 GB e8f8ca87 download
model-00018-of-00030.safetensors 4.66 GB 8e2b3f7c download
model-00023-of-00030.safetensors 4.66 GB 75f159e8 download
model-00028-of-00030.safetensors 4.66 GB b0bc3ba2 download
model-00003-of-00030.safetensors 4.66 GB 8d5118fb download
model-00029-of-00030.safetensors 4.63 GB 1adb7fd8 download
model-00009-of-00030.safetensors 4.63 GB 8d88d84c download
model-00014-of-00030.safetensors 4.63 GB 1f5e356b download
model-00019-of-00030.safetensors 4.63 GB 4d0d8e3a download
model-00024-of-00030.safetensors 4.63 GB 706adbc3 download
model-00004-of-00030.safetensors 4.63 GB c973a9b3 download
model-00006-of-00030.safetensors 4.34 GB cc61ccf5 download
model-00007-of-00030.safetensors 4.34 GB dde1ff8c download
model-00011-of-00030.safetensors 4.34 GB 125a0e4f download
model-00012-of-00030.safetensors 4.34 GB f395fc91 download
model-00016-of-00030.safetensors 4.34 GB cc286731 download
model-00017-of-00030.safetensors 4.34 GB 2da5e8e7 download
model-00021-of-00030.safetensors 4.34 GB 33dc20f7 download
model-00022-of-00030.safetensors 4.34 GB 8280eae1 download
model-00026-of-00030.safetensors 4.34 GB ee6a8272 download
model-00027-of-00030.safetensors 4.34 GB 3a22362b download
model-00002-of-00030.safetensors 4.34 GB a3676d54 download
model-00005-of-00030.safetensors 4.34 GB 717c370d download
model-00010-of-00030.safetensors 4.34 GB b8691a76 download
model-00015-of-00030.safetensors 4.34 GB 23824d46 download
model-00020-of-00030.safetensors 4.34 GB 605433e0 download
model-00025-of-00030.safetensors 4.34 GB 2451e434 download
model-00001-of-00030.safetensors 4.27 GB 70f2eac3 download
model-00030-of-00030.safetensors 1.96 GB 8185e676 download
tokenizer.json 8.66 MB a3c73537 download
model.safetensors.index.json 58.2 KB 37b1afe6 download
tokenizer_config.json 49.8 KB bdcb8c50 download
.gitattributes 3.55 KB 1efa72fc download
config.json 738 B 92c74c1c download
special_tokens_map.json 446 B 4dd5e992 download
generation_config.json 277 B 8726aaf0 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