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

Nexesenex/Llama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion

Nexesenex 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/Nexesenex%2FLlama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion"
Response includes
  • classification m5
  • files 38
  • hub_downloads_all_time 61
  • 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
61
24 last 30d - stable
Likes
0
Descendants
2
in 2 direct forks
Model age
18mo ago
created 2025-04-15
Downloads over time
Now71→from0↑0%
02652780 on Apr 9, 202571 on Oct 1271 on Oct 8Apr '25Jul '25Oct '25JanAprJulOct
Apr 9, 2025 → Oct 12 · 119 snapshots · spans 551 days

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.

NexesMess/Llama_3.x_70b_L3.3_TDRussel-Storywriter_128K_v1.02 this lineage
Nexesenex/Llama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion↓ 24 2 forks
mradermacher/Llama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion-i1-GGUF↓ 645
mradermacher/Llama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion-GGUF↓ 222

Metadata

Tags
transformers safetensors llama text-generation mergekit merge conversational base_model:NexesMess/Llama_3.x_70b_L3.3_TDRussel-Storywriter_128K_v1.02 base_model:merge:NexesMess/Llama_3.x_70b_L3.3_TDRussel-Storywriter_128K_v1.02 base_model:nbeerbower/Llama3.1-Gutenberg-Doppel-70B base_model:merge:nbeerbower/Llama3.1-Gutenberg-Doppel-70B text-generation-inference

Related

Other by Nexesenex
Dolphin3.0-Llama3.1-1B-abliterated 37 pankajmathur_orca_mini_v9_6_1B-instruct-Abliterated-LPL 26 Llama_3.x_70b_DoppelGutenberg-L3.3_abliterated_fusion 26 Llama_3.x_70b_Nemotron-L3.3_abliterated_fusion_v2 23 Llama_3.x_70b_L3.3-Nemotron_abliterated_fusion 20
Total size
131 GB
Files
38
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-04-16 17:56
Source huggingface.co/Nexesenex/Llama_3.x_70b_Gutenberg-Doppel-L3.3-TDRussel-Storywriter_abliterated_fusion ↗ Base model NexesMess/Llama_3.x_70b_L3.3_TDRussel-Storywriter_128K_v1.02 ↗

Files by quantization

Auxiliary files 38 files 131 GB
model-00004-of-00030.safetensors 4.66 GB 267bb0f0 download
model-00009-of-00030.safetensors 4.66 GB 34fd5233 download
model-00019-of-00030.safetensors 4.66 GB 1cbca5bd download
model-00024-of-00030.safetensors 4.66 GB bb2e7207 download
model-00014-of-00030.safetensors 4.66 GB 0f7440f1 download
model-00029-of-00030.safetensors 4.66 GB 472865c1 download
model-00003-of-00030.safetensors 4.64 GB e71f04cc download
model-00008-of-00030.safetensors 4.64 GB b9660614 download
model-00013-of-00030.safetensors 4.64 GB d56dac72 download
model-00023-of-00030.safetensors 4.64 GB 15dc92ae download
model-00028-of-00030.safetensors 4.64 GB e63338d8 download
model-00018-of-00030.safetensors 4.64 GB d7e6d125 download
model-00001-of-00030.safetensors 4.35 GB 7c4a5cdb download
model-00007-of-00030.safetensors 4.34 GB c4e40076 download
model-00012-of-00030.safetensors 4.34 GB ce52867c download
model-00017-of-00030.safetensors 4.34 GB 1ab6f687 download
model-00027-of-00030.safetensors 4.34 GB 700596d0 download
model-00011-of-00030.safetensors 4.34 GB b2978e1b download
model-00016-of-00030.safetensors 4.34 GB 118aecc1 download
model-00021-of-00030.safetensors 4.34 GB 9680b2b2 download
model-00022-of-00030.safetensors 4.34 GB b2e70077 download
model-00002-of-00030.safetensors 4.34 GB 1b8569f4 download
model-00006-of-00030.safetensors 4.34 GB d1c417df download
model-00026-of-00030.safetensors 4.34 GB f803d6ca download
model-00005-of-00030.safetensors 4.33 GB 430b1e16 download
model-00015-of-00030.safetensors 4.33 GB 8449588d download
model-00020-of-00030.safetensors 4.33 GB 1da040bb download
model-00025-of-00030.safetensors 4.33 GB 5f3b9e9c download
model-00010-of-00030.safetensors 4.33 GB 4ea6e79e download
model-00030-of-00030.safetensors 1.86 GB e999661f download
tokenizer.json 16.4 MB 14cc2c3b download
tokenizer_config.json 56.0 KB 429e536d download
model.safetensors.index.json 55.4 KB 2ef670b5 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.32 KB b176f237 download
config.json 886 B d1dd24f0 download
mergekit_config.yml 496 B 06aaf817 download
special_tokens_map.json 444 B 44e8cb89 download

README current version from Hugging Face

base_model:

  • NexesMess/Llama_3.x_70b_L3.3_TDRussel-Storywriter_128K_v1.02
  • nbeerbower/Llama3.1-Gutenberg-Doppel-70B
    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 nbeerbower/Llama3.1-Gutenberg-Doppel-70B 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: nbeerbower/Llama3.1-Gutenberg-Doppel-70B
    parameters:
      weight: 1.0
  - model: NexesMess/Llama_3.x_70b_L3.3_TDRussel-Storywriter_128K_v1.02
    parameters:
      weight: 1.0
base_model: nbeerbower/Llama3.1-Gutenberg-Doppel-70B
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 1 version

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

  1. 2025-04-15Upload folder using huggingface_hub882967c1.3 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