license: apache-2.0
base_model: Qwen/Qwen3-8B
tags:

• uncensored
• abliterated
• qwen3
• dolphin
• sft
• trc
  language:
• en
  pipeline_tag: text-generation
  model-index:
• name: dolphin-v2-8b-abliterated
  results:
  • task:
    type: multiple-choice
    name: ARC Challenge
    dataset:
    name: ARC Challenge
    type: ai2_arc
    config: ARC-Challenge
    split: test
    metrics:
    • type: acc
      value: 56.5
      name: Accuracy
    • type: acc_norm
      value: 54.0
      name: Normalized Accuracy
  • task:
    type: multiple-choice
    name: HellaSwag
    dataset:
    name: HellaSwag
    type: Rowan/hellaswag
    split: validation
    metrics:
    • type: acc_norm
      value: 64.5
      name: Normalized Accuracy
  • task:
    type: multiple-choice
    name: TruthfulQA MC2
    dataset:
    name: TruthfulQA
    type: truthful_qa
    config: multiple_choice
    split: validation
    metrics:
    • type: acc
      value: 48.8
      name: Accuracy
  • task:
    type: multiple-choice
    name: Winogrande
    dataset:
    name: Winogrande
    type: winogrande
    config: winogrande_xl
    split: validation
    metrics:
    • type: acc
      value: 57.0
      name: Accuracy

Dolphin V2 8B Abliterated

An uncensored 8B parameter language model built on Qwen3-8B, fine-tuned on 1.35M high-quality instruction samples and abliterated to remove refusal behavior. Developed for TRC (TPU Research Cloud) research.

Model Details

• Architecture: Qwen3ForCausalLM (36 layers, 4096 hidden, 32 attn heads, 8 KV heads)
• Parameters: 8.2B
• Context Length: 4096 (trained), 40960 (max supported)
• Precision: bfloat16
• License: Apache 2.0

Training

SFT Phase

• Base model: Qwen/Qwen3-8B
• Hardware: Google Cloud TPU v6e-16 (spot)
• Framework: MaxText (JAX)
• Steps: 130,000 (~3 epochs)
• Learning rate: 5e-6 with cosine decay
• Warmup: 200 steps
• Effective batch size: 16
• Sequence length: 4096

Training Dataset (1.35M samples)

All data was filtered to remove refusal patterns, safety-alignment subsets, and <think> reasoning tags.

Abliteration Phase

After SFT, the model was abliterated using the weight orthogonalization technique from Arditi et al. (2024) to remove residual refusal behavior.

• Technique: Multi-direction abliteration (weight orthogonalization)
• Directions removed: 5
• Target layers: 35, 34, 36, 33, 16 (selected by highest refusal direction scores)
• Samples used: 256 harmful/harmless instruction pairs
• Method: For each selected layer, the refusal direction was identified via mean difference between harmful and harmless activations, then orthogonalized out of the weight matrices.

Benchmark Results

Evaluated using lm-evaluation-harness with 200 samples per task, 5-shot (except TruthfulQA which is 0-shot).

GGUF Quantizations

Usage with llama.cpp

llama-server -m dolphin-v2-8b-abliterated-Q8_0.gguf -ngl 99 -c 4096

Usage with Ollama

# Create a Modelfile
echo 'FROM ./dolphin-v2-8b-abliterated-Q8_0.gguf' > Modelfile
ollama create dolphin-v2-abliterated -f Modelfile
ollama run dolphin-v2-abliterated

Usage with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("0arch-io/dolphin-v2-8b-abliterated", torch_dtype="bfloat16", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("0arch-io/dolphin-v2-8b-abliterated")

messages = [{"role": "user", "content": "Hello, how are you?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
outputs = model.generate(inputs, max_new_tokens=512, temperature=0.7)
print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True))

Disclaimer

This is a research model with no content filters. It will comply with any request without refusing. The creators are not responsible for how this model is used. Use responsibly.

Acknowledgments

• Qwen team for the Qwen3-8B base model
• Google TRC for TPU compute
• NousResearch for the Hermes-3 dataset
• Arditi et al. for the abliteration technique
• Built with MaxText on Google Cloud TPU