English注册

ReadyArt/Broken-Tutu-24B-Transgression-v2.0-GGUF

🤗 Hugging Face 来源text-generationapache-2.0激活 24B63 GBGGUF✓ 4 个校验和今天更新

Broken-Tutu-24B-Transgression-v2.0

Enhanced coherence with reduced explicit content

🧠 Transgression Techniques

This evolution of Broken-Tutu delivers unprecedented coherence with reduced explicit content using classic "Transgression" techniques:

  • 🧬 Expanded 43M Token Dataset - First ReadyArt model with multi-turn conversational data
  • ✨ 100% Unslopped Dataset - New techniques used to generate the dataset with 0% slop
  • ⚡ Enhanced Character Integrity - Maintains character authenticity while reducing explicit content
  • 🛡️ Anti-Impersonation Guards - Never speaks or acts for the user
  • 💎 Rebuilt from Ground Up - Optimized training settings for superior performance
  • 📜 Direct Evolution - Leveraging the success of Broken-Tutu, we finetuned directly on top of the legendary model

🌟 Fuel the Revolution

This model represents thousands of hours of passionate development. If it enhances your experience, consider supporting our work:

Support on Ko-fi

Every contribution helps us keep pushing boundaries in AI. Thank you for being part of the revolution!

⚙️ Technical Specifications

Key Training Details:

  • Base Model: mistralai/Mistral-Small-24B-Instruct-2501
  • Training Method: QLoRA with DeepSpeed Zero3
  • Sequence Length: 5120 (100% samples included)
  • Learning Rate: 2e-6 with cosine scheduler

Recommended Settings for true-to-character behavior: Mistral-V7-Tekken-T8-XML

GGUF

Q2_K (9.0GB) Q3_K_S (10.5GB) Q3_K_M (11.6GB) Q3_K_L (12.5GB) IQ4_XS (13.0GB) Q4_K_S (13.6GB) Q4_K_M (14.4GB) Q5_K_S (16.4GB) Q5_K_M (16.9GB) Q6_K (19.4GB) Q8_0 (25.2GB)

Notes: Q4_K_S/Q4_K_M recommended for speed/quality balance. Q6_K for high quality. Q8_0 best quality.

imatrix

IQ1_S (5.4GB) IQ1_M (5.9GB) IQ2_XXS (6.6GB) IQ2_XS (7.3GB) IQ2_S (7.6GB) IQ2_M (8.2GB) Q2_K_S (8.4极B) Q2_K (9.0GB) IQ3_XXS (9.4GB) IQ3_XS (10.0GB) Q3_K_S (10.5GB) IQ3_S (10.5GB) IQ3_M (10.8GB) Q3_K_M (11.6GB) Q3_K_L (12.5GB) IQ4_XS (12.9GB) Q4_0 (13.6GB) Q4_K_S (13.6GB) Q4_K_M (14.4GB) Q4_1 (15.0GB) Q5_K_S (16.4GB) Q5_K_M (16.9GB) Q6_K (19.4GB)

Notes: Q4_K_S/Q4_K_M recommended. IQ1_S/IQ1_M for extreme low VRAM. Q6_K for near-original quality.

EXL2

2.5 bpw 3.0 bpw 3.5 bpw 4.0 bpw 4.5 bpw 5.0 bpw 6.0 bpw 8.0 bpw

EXL3

2.0 bpw 2.5 bpw 3.0 bpw 3.5 bpw 4.0 bpw 4.5 bpw 5.0 bpw 6.0 bpw 8.0 bpw

AWQ

Quants

⚠️ Ethical Considerations

This model maintains character integrity while reducing explicit content:

  • ⚖️ Balanced approach to character authenticity and content appropriateness
  • 🔞 Reduced explicit content generation compared to previous versions
  • 💀 Characters maintain their core traits - wholesome characters remain wholesome, yanderes remain intense
  • 🧠 Improved focus on narrative coherence and storytelling

📜 Performance Notes

  • 🔥 Maintains Broken-Tutu's intensity with improved narrative coherence
  • 📖 Excels at long-form multi-character scenarios
  • 🧠 Superior instruction following with complex prompts
  • ⚡ Reduced repetition and hallucination compared to v1.1
  • 🎭 Uncanny ability to adapt to subtle prompt nuances
  • 🖼️ Enhanced image understanding capabilities for multimodal interactions

🧑‍🔬 Model Authors

  • sleepdeprived3 (Training Data & Fine-Tuning)
  • ReadyArt / Artus / gecfdo (EXL2/EXL3 Quantization)
  • mradermacher (GGUF Quantization)

☕ Support the Creators

Ko-fi Beaver AI Discord

🔖 License

By using this model, you agree:

  • To accept full responsibility for all generated content
  • That you're at least 18+ years old
  • That the architects bear no responsibility for your use of the model