3.1 GB
12 files
Updated 4 months ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| .gitattributes | 1.57 kB xet | aacf151a | |
| README.md | 1.44 kB xet | 98551f3a | |
| abliteration_metadata.json | 1.69 kB xet | ba469b80 | |
| app.py | 3.04 kB xet | bc88e1a5 | |
| chat_template.jinja | 2.51 kB xet | ff383ecd | |
| config.json | 1.37 kB xet | b92844c1 | |
| generation_config.json | 242 Bytes xet | 5c9fc1b5 | |
| model-00001-of-00002.safetensors | 1.98 GB xet | f5782c61 | |
| model-00002-of-00002.safetensors | 1.11 GB xet | 9d83eb36 | |
| model.safetensors.index.json | 27.7 kB xet | 628e456f | |
| tokenizer.json | 11.4 MB xet | fa975915 | |
| tokenizer_config.json | 694 Bytes xet | e2b1c421 |
🤖 Qwen-Obliteratus Chatbot Model
Welcome to the official repository for Qwen-Obliteratus, a highly capable and robust chatbot model built upon the powerful Qwen architecture. Designed to "obliterate" complex conversational tasks, this model has been fine-tuned to deliver highly accurate, coherent, and engaging responses across a wide variety of domains.
✨ Model Highlights
- Advanced Conversational Skills: Optimized for multi-turn dialogues, maintaining context and coherence over long conversations.
- High Instruction Following: Excellent at understanding and executing complex user prompts, formatting requests, and roleplay.
- Robust Reasoning: Enhanced logical deduction and problem-solving capabilities compared to the base model.
- Safe & Aligned: Fine-tuned with a focus on helpfulness while minimizing harmful or biased outputs.
🚀 How to Get Started
You can easily load and use Qwen-Obliteratus using the transformers library.
Installation
Make sure you have the latest version of transformers installed:
pip install transformers torch accelerate
- Total size
- 3.1 GB
- Files
- 12
- Last updated
- Jun 17
- Pre-warmed CDN
- US EU US EU