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

KebalBaguette/aya-expanse-8b-abliterated-AWQ

KebalBaguette 7.0B 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/KebalBaguette%2Faya-expanse-8b-abliterated-AWQ"
Response includes
  • classification m1
  • files 12
  • hub_downloads_all_time 65
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=KebalBaguette
All 4 models by KebalBaguette
 GET/methods/m1
What "m1" means · taxonomy
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)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
65
11 last 30d - stable
Likes
0
Model age
4mo ago
created 2026-05-19
Downloads over time
Now67→from43↑56%
024497343 on May 2067 on Oct 1167 on Oct 2MayJunJulAugSepOct
May 20 → Oct 11 · 60 snapshots · spans 144 days

Genealogy 0 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.

lenML/aya-expanse-8b-abliterated↓ 264 this lineage
KebalBaguette/aya-expanse-8b-abliterated-AWQ↓ 11

Metadata

License
cc-by-nc-4.0
Languages
fr en
Tags
safetensors cohere aya abliterated uncensored awq compressed-tensors quantized fr en base_model:lenML/aya-expanse-8b-abliterated base_model:quantized:lenML/aya-expanse-8b-abliterated

Related

Other by KebalBaguette
Qwen2.5-7B-Instruct-abliterated-v2-AWQ 3K Mistral-Nemo-Instruct-2407-abliterated-AWQ 59 Mistral-7B-Instruct-v0.3-abliterated-AWQ 10
Same base model
mradermacher/aya-expanse-8b-abliterated-i1-GGUF 1K mradermacher/aya-expanse-8b-abliterated-GGUF 609 MaziyarPanahi/aya-expanse-8b-abliterated-GGUF 297 KYUNGYONG/aya-expanse-8b-abliterated-Q4-mlx 63 matrixportalx/aya-expanse-8b-abliterated-Q4_0-GGUF 39
Total size
5.33 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-19 16:22
Source huggingface.co/KebalBaguette/aya-expanse-8b-abliterated-AWQ ↗ Base model lenML/aya-expanse-8b-abliterated →

Files by quantization

Auxiliary files 12 files 5.35 GB
model-00001-of-00002.safetensors 4.64 GB 1b22aa93 download
model-00002-of-00002.safetensors 707 MB 74afb7a3 download
tokenizer.json 19.2 MB 80f84076 download
model.safetensors.index.json 80.3 KB b06adb6a download
tokenizer_config.json 7.10 KB f58d6299 download
README.md 1.96 KB 1d775129 download
config.json 1.57 KB f96c9878 download
.gitattributes 1.53 KB 52373fe2 download
chat_template.jinja 1.29 KB eea053cd download
recipe.yaml 755 B 4f784397 download
special_tokens_map.json 439 B cf33f2e5 download
generation_config.json 137 B 637b20dd download

README current version from Hugging Face

license: cc-by-nc-4.0
base_model: lenML/aya-expanse-8b-abliterated
tags:

  • cohere
  • aya
  • abliterated
  • uncensored
  • awq
  • compressed-tensors
  • quantized
    language:
  • fr
  • en

Aya Expanse 8B Abliterated — AWQ (W4A16)

AWQ 4-bit quantization of lenML/aya-expanse-8b-abliterated,
itself an abliteration of Aya Expanse 8B.

Why this exists

The base abliterated model was only published in BF16 and GGUF. This AWQ quant
serves natively in vLLM with the Marlin kernel for fast inference.

Quantization details

  • Tool: llm-compressor (vLLM project)
  • Format: compressed-tensors (auto-detected by vLLM)
  • Scheme: W4A16_ASYM (4-bit asymmetric weights, group_size 128, 16-bit activations)
  • Algorithm: AWQ (Activation-aware Weight Quantization)
  • Calibration: 128 French samples × 192 tokens from wikimedia/wikipedia (20231101.fr)
  • lm_head left in fp16 (preserves output quality)
  • Note: v_proj → o_proj smoothing is skipped on all 32 layers due to GQA shape mismatch (32 query heads / 8 KV heads). Standard AWQ behaviour for GQA models — quality impact is marginal since the input_layernorm → q/k/v smoothing remains active.

Usage with vLLM

vllm serve KebalBaguette/aya-expanse-8b-abliterated-AWQ \
  --quantization compressed-tensors \
  --tool-call-parser hermes \
  --enable-auto-tool-choice \
  --max-model-len 8192

License

CC-BY-NC-4.0 — non-commercial use only. Inherited from Cohere Aya Expanse 8B and lenML's abliterated derivative. This abliterated derivative is for research, personal, and non-commercial evaluation use only. For commercial deployment, contact Cohere for licensing, or use an Apache-licensed alternative (e.g. Mistral 7B / Nemo).

README history 1 version

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

  1. 2026-05-19AWQ 4-bit quantization of Aya Expanse 8B Abliterated with FR calibrationbf248ab2 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