quantfactory/llama-3.1-8b-arliai-rpmax-v1.1-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "llama3.1",
    "frontmatter": {},
    "hero_image_url": "https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ",
    "summary": "This is quantized version of ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1 created using llama.cpp # Original Model Card # Llama-3.1-8B-ArliAI-RPMax-v1.1 =====================================",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "\n---\n\nlicense: llama3.1\n\n---\n\n![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)\n\n# QuantFactory/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF\nThis is quantized version of [ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1](https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1) created using llama.cpp\n\n# Original Model Card\n\n\n# Llama-3.1-8B-ArliAI-RPMax-v1.1\n=====================================\n\n## Overview\n\nThis repository is based on the Meta-Llama-3.1-8B-Instruct model and is governed by the Meta Llama 3.1 License agreement: https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct\n\n## Model Description\n\nLlama-3.1-8B-ArliAI-RPMax-v1.1 is a variant of the Meta-Llama-3.1-8B model, trained on a diverse set of curated RP datasets with a focus on variety and deduplication. This model is designed to be highly creative and non-repetitive, with a unique approach to training that minimizes repetition.\n\nv1.1 is just a small fix to not train and save the embeddings layer, since v1.0 had the lm_head unnecessarily trained on accident.\n\nYou can access the model at https://arliai.com and ask questions at https://www.reddit.com/r/ArliAI/\n\n### Training Details\n\n* **Sequence Length**: 8192\n* **Training Duration**: Approximately 1 day on 2x3090Ti\n* **Epochs**: 1 epoch training for minimized repetition sickness\n* **LORA**: 64-rank 128-alpha, resulting in ~2% trainable weights\n* **Learning Rate**: 0.00001\n* **Gradient accumulation**: Very low 32 for better learning.\n\n## Quantization\n\nThe model is available in quantized formats:\n\n* **FP16**: https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1\n* **GGUF**: https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF\n\n## Suggested Prompt Format\n\nLlama 3 Instruct Format\n\nExample:\n```\n<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are [character]. You have a personality of [personality description]. [Describe scenario]<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n```\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "license:llama3.1",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 2,
  "downloads": 130,
  "gated": false,
  "private": false,
  "last_modified": "2024-08-26T07:16:43.000Z",
  "created_at": "2024-08-26T06:35:59.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66cc224f18989c3ca242363c",
  "id": "QuantFactory/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF",
  "modelId": "QuantFactory/Llama-3.1-8B-ArliAI-RPMax-v1.1-GGUF",
  "sha": "c8557309afbd5ed6974d8299b9c3e8cb764b9456",
  "createdAt": "2024-08-26T06:35:59.000Z",
  "lastModified": "2024-08-26T07:16:43.000Z",
  "author": "QuantFactory",
  "downloads": 130,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 16
}