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

Nexesenex/Llama_3.x_70b_FLDx2-L3.3_abliterated_fusion_norm

Nexesenex Llama 71B 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/Nexesenex%2FLlama_3.x_70b_FLDx2-L3.3_abliterated_fusion_norm"
Response includes
  • classification m5
  • files 38
  • benchmarks 11 entries
  • hub_downloads_all_time 88
  • author_summary 15 models
  • readme_text full
Try next
GET/models?author=Nexesenex
All 15 models by Nexesenex
 GET/models?family=llama&method=m5
Sibling llama models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
How we label → About M5 →
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
88
17 last 30d - stable
Likes
0
Descendants
2
in 2 direct forks
Model age
18mo ago
created 2025-04-10
Downloads over time
Now98→from6↑1,533%
137721076 on Apr 9, 202598 on Oct 11Apr '25Jul '25Oct '25JanAprJulOct
Apr 9, 2025 → Oct 11 · 118 snapshots · spans 550 days

Benchmarks

Benchmark Score Source
Entertainment 3.2 UGI
Hazardous 3.5 UGI
Natural Intelligence 33.54 UGI
Political lean -20.3% UGI
Sensitive-Info 32.66 UGI
SocPol 3.1 UGI
UGI 48.44 UGI
Willingness (10) 8 UGI
W10-Adherence 8 UGI
W10-Direct 8 UGI
Writing 31.76 UGI

Genealogy 2 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.

huihui-ai/Llama-3.3-70B-Instruct-abliterated↓ 16,741 this lineage
Nexesenex/Llama_3.x_70b_FLDx2-L3.3_abliterated_fusion_norm↓ 17 2 forks
mradermacher/Llama_3.x_70b_FLDx2-L3.3_abliterated_fusion_norm-i1-GGUF↓ 354
mradermacher/Llama_3.x_70b_FLDx2-L3.3_abliterated_fusion_norm-GGUF↓ 156

Metadata

Tags
transformers safetensors llama text-generation mergekit merge conversational base_model:hitachi-nlp/Llama-3.1-70B-FLDx2 base_model:merge:hitachi-nlp/Llama-3.1-70B-FLDx2 base_model:huihui-ai/Llama-3.3-70B-Instruct-abliterated base_model:merge:huihui-ai/Llama-3.3-70B-Instruct-abliterated text-generation-inference

Related

Other by Nexesenex
Dolphin3.0-Llama3.1-1B-abliterated 35 pankajmathur_orca_mini_v9_6_1B-instruct-Abliterated-LPL 27 Llama_3.x_70b_DoppelGutenberg-L3.3_abliterated_fusion 25 Llama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion 24 Llama_3.x_70b_Nemotron-L3.3_abliterated_fusion_v2 22
Same base model
bartowski/Llama-3.3-70B-Instruct-abliterated-GGUF 54K mradermacher/Llama-3.3-70B-Instruct-abliterated-GGUF 2K divinetribe/Llama-3.3-70B-Instruct-abliterated-8bit-mlx 1K jiangchengchengNLP/llama3.3-70B-instruct-abliterated-awq 861 mradermacher/Llama-3.3-70B-Instruct-abliterated-i1-GGUF 860
Total size
131 GB
Files
38
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-04-12 13:16
Source huggingface.co/Nexesenex/Llama_3.x_70b_FLDx2-L3.3_abliterated_fusion_norm ↗ Base model huihui-ai/Llama-3.3-70B-Instruct-abliterated →

Files by quantization

Auxiliary files 38 files 131 GB
model-00004-of-00030.safetensors 4.66 GB b03121a2 download
model-00009-of-00030.safetensors 4.66 GB 755142dc download
model-00019-of-00030.safetensors 4.66 GB 0bc173ba download
model-00024-of-00030.safetensors 4.66 GB 6bf40857 download
model-00014-of-00030.safetensors 4.66 GB 6a6010ee download
model-00029-of-00030.safetensors 4.66 GB 5402ffb8 download
model-00003-of-00030.safetensors 4.64 GB e454fb69 download
model-00008-of-00030.safetensors 4.64 GB 604c1314 download
model-00013-of-00030.safetensors 4.64 GB 894c0987 download
model-00023-of-00030.safetensors 4.64 GB 41ae4a71 download
model-00028-of-00030.safetensors 4.64 GB d8ee429d download
model-00018-of-00030.safetensors 4.64 GB e0a0b007 download
model-00001-of-00030.safetensors 4.35 GB 803f3ab3 download
model-00007-of-00030.safetensors 4.34 GB 8d8a5528 download
model-00012-of-00030.safetensors 4.34 GB b7be0918 download
model-00017-of-00030.safetensors 4.34 GB 22d6033f download
model-00027-of-00030.safetensors 4.34 GB 7bc35fb5 download
model-00011-of-00030.safetensors 4.34 GB 0c55d217 download
model-00016-of-00030.safetensors 4.34 GB 66b0eef8 download
model-00021-of-00030.safetensors 4.34 GB d4d72bec download
model-00022-of-00030.safetensors 4.34 GB 6eba4ba3 download
model-00002-of-00030.safetensors 4.34 GB d12ad25c download
model-00006-of-00030.safetensors 4.34 GB ed7277e5 download
model-00026-of-00030.safetensors 4.34 GB 37ebde12 download
model-00005-of-00030.safetensors 4.33 GB 2acfd2d9 download
model-00015-of-00030.safetensors 4.33 GB 62f01457 download
model-00020-of-00030.safetensors 4.33 GB a444b82c download
model-00025-of-00030.safetensors 4.33 GB dee54108 download
model-00010-of-00030.safetensors 4.33 GB 59fcc62c download
model-00030-of-00030.safetensors 1.86 GB 649a747d download
tokenizer.json 16.4 MB da0a3059 download
model.safetensors.index.json 55.4 KB 2ef670b5 download
tokenizer_config.json 54.3 KB 8e9a45f6 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.21 KB bbd6315f download
config.json 867 B 82a450ea download
mergekit_config.yml 462 B 80296eb5 download
special_tokens_map.json 444 B b8ecdee8 download

README current version from Hugging Face

base_model:

  • huihui-ai/Llama-3.3-70B-Instruct-abliterated
  • hitachi-nlp/Llama-3.1-70B-FLDx2
    library_name: transformers
    tags:
  • mergekit
  • merge

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Arcee Fusion merge method using hitachi-nlp/Llama-3.1-70B-FLDx2 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: arcee_fusion
models:
  - model: hitachi-nlp/Llama-3.1-70B-FLDx2
    parameters:
      weight: 1.0
  - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
    parameters:
      weight: 1.0
base_model: hitachi-nlp/Llama-3.1-70B-FLDx2
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: false
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union

README history 2 versions

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

  1. 2025-04-12Upload folder using huggingface_hub1211ab41.2 KB
    Loading...
  2. 2025-04-11Upload folder using huggingface_hub6f6e44a1.2 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