license: mit
language:

• en
• zh
  tags:
• deepseek
• deepseek-v4.1
• deepseek-v4.1-flash
• deepseek-v4.1-flash-1017
• exl3
• abliterated
• uncensored
• tensorfold
• dgx-spark
• gb10
• moe
• image-text-to-text
  base_model: Mia-AiLab/DeepSeek-V4.1-Flash-1017-EXL3-EAQ-v1-2.9-bpw
  library_name: transformers
  pipeline_tag: image-text-to-text
  extra_gated_heading: Acknowledge the Responsible Use Agreement to access this repository
  extra_gated_description: Access is granted automatically after you agree to the terms below and submit the form.
  extra_gated_button_content: Agree and request access
  extra_gated_fields:
  Username: text
  Email: text
  Reason for intended use: text
  I am 18 years of age or older: checkbox
  I accept full responsibility for my inputs and any harm from generated content: checkbox
  I will not use this model for sexual exploitation or endangerment of minors: checkbox
  I will not use this model for self-harm, suicide promotion, illegal activity, harassment, doxxing, or fraud: checkbox
  I agree to comply with the upstream DeepSeek base-model license: checkbox
  I agree to the Responsible Use terms in this card: checkbox

DeepSeek-V4.1-Flash-1017 EXL3 2.9 bpw ABliterated

This is a full, self-contained EXL3 checkpoint produced by applying the Keys
abliteration overlay to the Mia-AiLab EAQ-v1 2.9 bpw pack.

Sources and attribution

The overlay changes only layers.10-35.attn.wo_b (104 tensors). All experts,
Engram, embed/head, vision, MTP and the remaining tensors are from the stock
pack. MTP dtypes are kept at stock F16 so the native TensorFold drafter reads
mtp.2.confidence_head.proj.weight correctly (n_cast_f32: 0 in ABLIT_META.json).

Format

39 model-*.safetensors EXL3 shards, plus config/tokenizer/index/encoding and
chat_template.jinja. This is the Mia EAQ layout read by the TensorFold
DeepSeek-V4.1 family; it is not a plain Transformers FP16 checkpoint.

Responsible Use

This model has had safety refusals removed, including cybersecurity offense and
defense rails. It is intended for red-teaming, security research, evaluation and
unfiltered assistant tasks. You are responsible for adding appropriate safety
filtering, human review and access controls for your deployment.

Prohibited uses:

• anything involving the sexual exploitation or endangerment of minors;
• content promoting self-harm or suicide;
• material illegal in your jurisdiction, or targeting real individuals for
  harassment, doxxing or fraud;
• any use prohibited by the upstream DeepSeek license.

You must be 18 or older. The checkpoint is provided as-is, with no warranty.