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

grimjim/Llama-3.1-Supernova-Lite-Instruct-merge-abliterated-8B

grimjim Llama 8.0B 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/grimjim%2FLlama-3.1-Supernova-Lite-Instruct-merge-abliterated-8B"
Response includes
  • classification m5
  • files 14
  • benchmarks 5 entries
  • hub_downloads_all_time 204
  • author_summary 14 models
  • readme_text full
Try next
GET/models?author=grimjim
All 14 models by grimjim
 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
204
26 last 30d - stable
Likes
1
Descendants
2
in 2 direct forks
Model age
2.1y ago
created 2024-09-13
Downloads over time
Now214→from8↑2,575%
0781572358 on Sep 11, 2024214 on Oct 11214 on Oct 9Sep '24Jan '25May '25Sep '25JanMaySep
Sep 11, 2024 → Oct 11 · 148 snapshots · spans 760 days

Benchmarks

Benchmark Score Source
BBH average 0.4689324166558567 OpenLLM-v2
IFEval instruct 0.5635491606714629 OpenLLM-v2
IFEval-Prompt 0.41035120147874304 OpenLLM-v2
MATH lvl 5 0.12386706948640483 OpenLLM-v2
MMLU-Pro 0.3651097074468085 OpenLLM-v2

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.

grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter↓ 74 this lineage
grimjim/Llama-3.1-Supernova-Lite-Instruct-merge-abliterated-8B↓ 26 2 forks
mradermacher/Llama-3.1-Supernova-Lite-Instruct-merge-abliterated-8B-i1-GGUF↓ 621
mradermacher/Llama-3.1-Supernova-Lite-Instruct-merge-abliterated-8B-GGUF↓ 344

Metadata

License
llama3.1
Tags
transformers safetensors llama text-generation mergekit merge conversational base_model:grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter base_model:merge:grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter base_model:grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B base_model:merge:grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B license:llama3.1

Related

Other by grimjim
Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF 592 gemma-3-12b-it-abliterated-GGUF 139 gemma-3-12b-it-norm-preserved-biprojected-abliterated 88 Llama-3.1-8B-Instruct-abliterated_via_adapter 74 gemma-3-12b-it-projection-abliterated 63
Same base model
featherless-ai-quants/grimjim-Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF 1K mradermacher/Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF 699 grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF 592 tensorblock/Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF 65 NikolayKozloff/Llama-3.1-8B-Instruct-abliterated_via_adapter-Q8_0-GGUF 42
Total size
15.0 GB
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-09-13 04:41
Source huggingface.co/grimjim/Llama-3.1-Supernova-Lite-Instruct-merge-abliterated-8B ↗ Base model grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter →

Files by quantization

Auxiliary files 14 files 15.0 GB
model-00002-of-00004.safetensors 4.66 GB 2a591862 download
model-00001-of-00004.safetensors 4.61 GB 5a5815ae download
model-00003-of-00004.safetensors 4.58 GB 9f804188 download
model-00004-of-00004.safetensors 1.11 GB e750a519 download
tokenizer.json 8.66 MB 79e3e522 download
tokenizer_config.json 49.7 KB 421cda36 download
model.safetensors.index.json 22.3 KB 127562b3 download
LICENSE 7.62 KB 4c763399 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.23 KB 77c9f4a2 download
config.json 940 B d74a94b3 download
special_tokens_map.json 296 B 02ee80b6 download
mergekit_config.yml 270 B 272511b9 download
Notice 122 B 5fd89229 download

README current version from Hugging Face

base_model:

  • grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter
  • grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
    library_name: transformers
    pipeline_tag: text-generation
    tags:
  • mergekit
  • merge
    license: llama3.1

Llama-3.1-Supernova-Lite-Instruct-merge-abliterated-8B

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

Built with Llama.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter
  - model: grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
merge_method: slerp
base_model: grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter
parameters:
  t:
   - value: 0.5
dtype: bfloat16

README history 2 versions

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

  1. 2024-09-13Initial release169d7401.2 KB
    Loading...
  2. 2024-09-13initial commit76d7e7d26 B
    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