Hercules-Qwen1.5-14B

<style> body { font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; line-height: 1.6; color: #f5f5f5; background-color: #1e2a36; margin: 0; padding: 0; } .container { max-width: 1200px; margin: 20px auto; padding: 20px; background-color: #2a3f54; border-radius: 8px; box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1); display: flex; flex-wrap: wrap; justify-content: space-between; } h1 { font-size: 2.5rem; color: #51a3d3; text-align: center; margin-bottom: 30px; width: 100%; } h2 { font-size: 1.75rem; margin: 20px 0; color: #63b8ea; padding-bottom: 10px; } h3 { font-size: 1.25rem; color: #80c8f4; } p, a { font-size: 1rem; } p { color: #b0c2ce; margin-bottom: 20px; } ul { list-style-type: none; padding: 0; display: flex; flex-wrap: wrap; justify-content: space-between; width: 100%; } li { background-color: #34495e; padding: 20px; margin-bottom: 10px; border-radius: 4px; cursor: pointer; transition: background-color 0.3s ease, color 0.3s ease; overflow: hidden; color: #b0c2ce; width: calc(50% - 10px); box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1); } li:hover { background-color: #4e6a81; color: #dfe8f1; } .section-content { margin-top: 15px; border-top: 1px solid #4e6a81; padding-top: 10px; } a { color: #a4c8e1; text-decoration: none; } a:hover { text-decoration: underline; } pre { background-color: #2c3e50; padding: 10px; border-radius: 5px; overflow-x: auto; color: #b0c2ce; } </style> <div class="container"> <h1>Hercules-Qwen1.5-14B</h1> </div> <ul> <li> <h2>Model Details</h2> <div class="section-content"> <h3>Model Description</h3> <p>This model has capabilities in math, coding, function calling, roleplay, and more. We fine-tuned it using 700,000 examples of Hercules-v4.</p> <p><strong>Developed by:</strong> M4-ai</p> <p><strong>Language(s) (NLP):</strong> English and maybe Chinese</p> <p><strong>License:</strong> tongyi-qianwen license</p> <p><strong>Finetuned from model:</strong> <a href="https://huggingface.co/Qwen/Qwen1.5-14B">Qwen1.5-14B</a></p> </div> </li> <li> <h2>Uses</h2> <div class="section-content"> <p>General purpose assistant, question answering, chain-of-thought, etc..</p> <h3>Recommendations</h3> <p>Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.</p> </div> </li> <li> <h2>Evaluation</h2> <div class="section-content"> <p>Coming soon</p> </div> </li> <li> <h2>Training Details</h2> <div class="section-content"> <h3>Training Data</h3> <p><a href="https://huggingface.co/datasets/Locutusque/hercules-v4.0">https://huggingface.co/datasets/Locutusque/hercules-v4.0</a></p> <h4>Training Hyperparameters</h4> <p><strong>Training regime:</strong> bf16 non-mixed precision</p> </div> </li> <li> <h2>Technical Specifications</h2> <div class="section-content"> <h4>Hardware</h4> <p>We used 8 Kaggle TPUs, and we trained at a global batch size of 128 and sequence length of 1024</p> </div> </li> <li> <h2>Contributions</h2> <div class="section-content"> <p>Thanks to @Tonic, @aloobun, @fhai50032, and @Locutusque for their contributions to this model.</p> </div> </li> </ul>