Get the app
← back to catalog · registered 2026-11-01 02:01

fabricioslv/erika-qwen38-uncensored-agentic-merged

fabricioslv multimodal 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/fabricioslv%2Ferika-qwen38-uncensored-agentic-merged"
Response includes
  • classification m-uncensored
  • files 12
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=fabricioslv
All 3 models by fabricioslv
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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 · 30-day
8
Likes
0
Model age
1w ago
created 2026-10-24

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.

philbert440/Qwen3.8-27B-Uncensored-Cyber↓ 1,325 this lineage
fabricioslv/erika-qwen38-uncensored-agentic-merged↓ 8

Metadata

License
other
Tags
transformers safetensors qwen3_5 image-text-to-text erika omnimind merged bf16 conversational base_model:philbert440/Qwen3.8-27B-Uncensored-Cyber base_model:finetune:philbert440/Qwen3.8-27B-Uncensored-Cyber license:other

Related

Other by fabricioslv
erika-qwen38-uncensored-agentic-nf4 0 erika-qwen38-uncensored-agentic-q4_k_m-gguf 0
Same base model
philbert440/Qwen3.8-27B-Uncensored-Cyber-GGUF 538K cyjin-yl/Qwen3.8-27B-Uncensored-Cyber-agentic-imatrix-GGUF 299K philbert440/Qwen3.8-27B-Uncensored-Cyber-W4A16-AWQ 1K philbert440/Qwen3.8-27B-Uncensored-Cyber-NVFP4 502 philbert440/Qwen3.8-27B-Uncensored-Cyber-MLX-4bit 409
Total size
51.7 GB
Files
12
Quantizations
1
Registered
2026-11-01 02:01
Last updated on HF
2026-10-24 19:30
Source huggingface.co/fabricioslv/erika-qwen38-uncensored-agentic-merged ↗ Base model philbert440/Qwen3.8-27B-Uncensored-Cyber →

Files by quantization

Auxiliary files 12 files 51.8 GB
model-00001-of-00002.safetensors 46.4 GB 1b263707 download
model-00002-of-00002.safetensors 4.55 GB d2237021 download
model-mtp.safetensors 810 MB 90fa0e3e download
tokenizer.json 19.1 MB 06b95093 download
model.safetensors.index.json 105 KB 1a53e75c download
tokenizer_config.json 16.0 KB 7a496485 download
chat_template.jinja 8.74 KB c0c686f9 download
config.json 4.35 KB 466b4901 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.43 KB 4a445ed4 download
processor_config.json 1.19 KB 43c4343e download
generation_config.json 214 B c53835dc download

README current version from Hugging Face

license: other
base_model: philbert440/Qwen3.8-27B-Uncensored-Cyber
library_name: transformers
tags:

  • erika
  • omnimind
  • merged
  • bf16
  • qwen3_5

Erika Qwen3.8-27B Uncensored Agentic — Merged BF16

Full merged bf16 weights: base philbert440/Qwen3.8-27B-Uncensored-Cyber +
Erika QLoRA adapter (r=16/α=32, checkpoint-1400) merged via Unsloth on Colab L4.
This is the pre-GGUF artifact — real bf16 weights for probing, hidden-state
extraction (MPS Bridge), or further fine-tuning without dequantization.

Architecture: Qwen3_5ForConditionalGeneration (multimodal, hidden_size=5120,
includes model-mtp.safetensors MTP head).

Use

from transformers import AutoModelForImageTextToText, AutoTokenizer

model = AutoModelForImageTextToText.from_pretrained(
    "fabricioslv/erika-qwen38-uncensored-agentic-merged",
    torch_dtype="bfloat16", device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    "fabricioslv/erika-qwen38-uncensored-agentic-merged")

Related repos

  • fabricioslv/erika-qwen38-uncensored-agentic — LoRA adapter + trainer checkpoints (800–1400)
  • fabricioslv/erika-qwen38-uncensored-agentic-gguf — IQ4_XS serving build

Provenance

Trained 2026-10-07→08, notebook train_erika_qwen38_uncensored_l4.ipynb.
Safetensors exported by Unsloth pre-quantization; source folder
erika_qwen38_gguf/gguf_q4_k_m/ on Google Drive (folder name is historical —
contents are safetensors, not GGUF).

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