Aura-Llama-Abliterated

<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>Aura-llama-3 Data Card</title> <link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet"> <style> body { font-family: 'Quicksand', sans-serif; background: linear-gradient(135deg, #2E3440 0%, #1A202C 100%); color: #D8DEE9; margin: 0; padding: 0; font-size: 16px; } .container { width: 100%; max-width: 1440px; margin: 20px auto; background-color: rgba(255, 255, 255, 0.02); padding: 20px; border-radius: 12px; box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2); backdrop-filter: blur(10px); border: 1px solid rgba(255, 255, 255, 0.1); } .header h1 { font-size: 28px; color: #ECEFF4; margin: 0 0 20px 0; text-shadow: 2px 2px 4px rgba(0, 0, 0, 0.3); } .update-section { margin-top: 30px; } .update-section h2 { font-size: 24px; color: #88C0D0; } .update-section p { font-size: 16px; line-height: 1.6; color: #ECEFF4; } .info img { width: 100%; border-radius: 10px; margin-bottom: 15px; } a { color: #88C0D0; text-decoration: none; } a:hover { color: #A3BE8C; } pre { background-color: rgba(255, 255, 255, 0.05); padding: 10px; border-radius: 5px; overflow-x: auto; } code { font-family: 'Courier New', monospace; color: #A3BE8C; } </style> </head> <body> <div class="container"> <div class="header"> <h1>Aura-llama-3-Abliterated</h1> </div> <div class="info"> <img src="https://cdn-uploads.huggingface.co/production/uploads/64545af5ec40bbbd01242ca6/AwLNDVB-GIY7k0wnVV_TX.png" alt="Aura-llama-Abliterated Image"> <p>Now that the cute anime girl has your attention.</p> <p>UPDATE: Model is now using the abliterated version of meta llama 3 8b </p> <p>Aura-llama is using the methodology presented by SOLAR for scaling LLMs called depth up-scaling (DUS), which encompasses architectural modifications with continued pretraining. Using the solar paper as a base, I integrated Llama-3 weights into the upscaled layers, and In the future plan to continue training the model.</p> <p>Aura-llama is a merge of the following models to create a base model to work from:</p> <ul> <li><a href="https://huggingface.co/failspy/Llama-3-8B-Instruct-abliterated">failspy/Llama-3-8B-Instruct-abliterated</a></li> <li><a href="https://huggingface.co/failspy/Llama-3-8B-Instruct-abliterated">failspy/Llama-3-8B-Instruct-abliterated</a></li> </ul> </div> <div class="update-section"> <h2>Abliterated Merged Evals (Has Not Been Finetuned):</h2> <p>Aura-llama-Abliterated</p> <ul> <li>Avg: ?</li> <li>ARC: ?</li> <li>HellaSwag: ?</li> <li>MMLU: ?</li> <li>T-QA: ?</li> <li>Winogrande: ?</li> <li>GSM8K: ?</li> </ul> <h2>Non Abliterated Merged Evals (Has Not Been Finetuned):</h2> <p>Aura-llama-Original</p> <ul> <li>Avg: 63.13</li> <li>ARC: 58.02</li> <li>HellaSwag: 77.82</li> <li>MMLU: 65.61</li> <li>T-QA: 51.94</li> <li>Winogrande: 73.40</li> <li>GSM8K: 52.01</li> </ul> </div> <div class="update-section"> <h2>🧩 Configuration</h2> <pre><code> dtype: bfloat16 merge_method: passthrough slices: - sources: - layer_range: [0, 12] model: failspy/Llama-3-8B-Instruct-abliterated - sources: - layer_range: [8, 20] model: failspy/Llama-3-8B-Instruct-abliterated - sources: - layer_range: [16, 28] model: failspy/Llama-3-8B-Instruct-abliterated - sources: - layer_range: [24, 32] model: failspy/Llama-3-8B-Instruct-abliterated </code></pre> </div> </div> </body> </html>

Open LLM Leaderboard Evaluation Results

Detailed results can be found here