quantfactory/onellm-doey-chatqa-v1-llama-3.2-1b-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "datasets": [
      "nvidia/ChatQA-Training-Data"
    ],
    "language": [
      "en"
    ],
    "base_model": [
      "meta-llama/Llama-3.2-1B-Instruct"
    ],
    "pipeline_tag": "text-generation",
    "library_name": "transformers",
    "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 DoeyLLM/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B created using llama.cpp # Original Model Card",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "\n---\n\nlicense: apache-2.0\ndatasets:\n- nvidia/ChatQA-Training-Data\nlanguage:\n- en\nbase_model:\n- meta-llama/Llama-3.2-1B-Instruct\npipeline_tag: text-generation\nlibrary_name: transformers\n\n---\n\n[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)\n\n\n# QuantFactory/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF\nThis is quantized version of [DoeyLLM/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B](https://huggingface.co/DoeyLLM/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B) created using llama.cpp\n\n# Original Model Card\n\n## **Model Summary**\nThis model is a fine-tuned version of **LLaMA 3.2-1B**, optimized using **LoRA (Low-Rank Adaptation)** on the [NVIDIA ChatQA-Training-Data](https://huggingface.co/datasets/nvidia/ChatQA-Training-Data). It is tailored for conversational AI, question answering, and other instruction-following tasks, with support for sequences up to 1024 tokens.\n\n---\n\n## **Key Features**\n- **Base Model**: LLaMA 3.2-1B\n- **Fine-Tuning Framework**: LoRA\n- **Dataset**: NVIDIA ChatQA-Training-Data\n- **Max Sequence Length**: 1024 tokens\n- **Use Case**: Instruction-based tasks, question answering, conversational AI.\n\n## **Model Usage**\nThis fine-tuned model is suitable for:\n- **Conversational AI**: Chatbots and dialogue agents with improved contextual understanding.\n- **Question Answering**: Generating concise and accurate answers to user queries.\n- **Instruction Following**: Responding to structured prompts.\n- **Long-Context Tasks**: Processing sequences up to 1024 tokens for long-text reasoning.\n\n# **How to Use DoeyLLM / OneLLM-Doey-V1-Llama-3.2-1B-Instruct**\n\nThis guide explains how to use the **DoeyLLM** model on both app (iOS) and PC platforms.\n\n---\n\n## **App: Use with OneLLM**\n\nOneLLM brings versatile large language models (LLMs) to your device—Llama, Gemma, Qwen, Mistral, and more. Enjoy private, offline GPT and AI tools tailored to your needs.\n\nWith OneLLM, experience the capabilities of leading-edge language models directly on your device, all without an internet connection. Get fast, reliable, and intelligent responses, while keeping your data secure with local processing.\n\n### **Quick Start for mobile**\n\n\n![OneLLM](./OneLLM.png)\n\nFollow these steps to integrate the **DoeyLLM** model using the OneLLM app:\n\n1. **Download OneLLM**  \n   Get the app from the [App Store](https://apps.apple.com/us/app/onellm-private-ai-gpt-llm/id6737907910) and install it on your iOS device.\n\n   Or get the app from the [Play Store](https://play.google.com/store/apps/details?id=com.esotech.onellm) and install it on your Android device.\n\n3. **Load the DoeyLLM Model**  \n   Use the OneLLM interface to load the DoeyLLM model directly into the app:\n   - Navigate to the **Model Library**.\n   - Search for `DoeyLLM`.\n   - Select the model and tap **Download** to store it locally on your device.\n4. **Start Conversing**  \n   Once the model is loaded, you can begin interacting with it through the app's chat interface. For example:\n   - Tap the **Chat** tab.\n   - Type your question or prompt, such as:\n     > \"Explain the significance of AI in education.\"\n   - Receive real-time, intelligent responses generated locally.\n\n### **Key Features of OneLLM**\n- **Versatile Models**: Supports various LLMs, including Llama, Gemma, and Qwen.\n- **Private & Secure**: All processing occurs locally on your device, ensuring data privacy.\n- **Offline Capability**: Use the app without requiring an internet connection.\n- **Fast Performance**: Optimized for mobile devices, delivering low-latency responses.\n\nFor more details or support, visit the [OneLLM App Store page](https://apps.apple.com/us/app/onellm-private-ai-gpt-llm/id6737907910) and [Play Store](https://play.google.com/store/apps/details?id=com.esotech.onellm).\n\n## **PC: Use with Transformers**\n\nThe DoeyLLM model can also be used on PC platforms through the `transformers` library, enabling robust and scalable inference for various NLP tasks.\n\n### **Quick Start for PC**\nFollow these steps to use the model with Transformers:\n\n1. **Install Transformers**  \n   Ensure you have `transformers >= 4.43.0` installed. Update or install it via pip:\n\n   ```bash\n   pip install --upgrade transformers\n\n2. **Load the Model**  \n   Use the transformers library to load the model and tokenizer:\n\nStarting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.\n\nMake sure to update your transformers installation via `pip install --upgrade transformers`.\n\n```python\nimport torch\nfrom transformers import pipeline\n\nmodel_id = \"OneLLM-Doey-V1-Llama-3.2-1B\"\npipe = pipeline(\n    \"text-generation\",\n    model=model_id,\n    torch_dtype=torch.bfloat16,\n    device_map=\"auto\",\n)\nmessages = [\n    {\"role\": \"system\", \"content\": \"You are a pirate chatbot who always responds in pirate speak!\"},\n    {\"role\": \"user\", \"content\": \"Who are you?\"},\n]\noutputs = pipe(\n    messages,\n    max_new_tokens=256,\n)\nprint(outputs[0][\"generated_text\"][-1])\n```\n\n\n   \n## Responsibility & Safety\n\nAs part of our responsible release strategy, we adopted a three-pronged approach to managing trust and safety risks:\n\nEnable developers to deploy helpful, safe, and flexible experiences for their target audience and the use cases supported by the model.\nProtect developers from adversarial users attempting to exploit the model’s capabilities to potentially cause harm.\nProvide safeguards for the community to help prevent the misuse of the model.\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "text-generation",
    "en",
    "dataset:nvidia/ChatQA-Training-Data",
    "base_model:meta-llama/Llama-3.2-1B-Instruct",
    "base_model:quantized:meta-llama/Llama-3.2-1B-Instruct",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 5,
  "downloads": 363,
  "gated": false,
  "private": false,
  "last_modified": "2024-11-25T10:27:03.000Z",
  "created_at": "2024-11-25T10:18:19.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "67444eeb2749138c01f5cbb6",
  "id": "QuantFactory/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF",
  "modelId": "QuantFactory/OneLLM-Doey-ChatQA-V1-Llama-3.2-1B-GGUF",
  "sha": "5e2bf1e947b1ffde50b06467ff913a1078ad674f",
  "createdAt": "2024-11-25T10:18:19.000Z",
  "lastModified": "2024-11-25T10:27:03.000Z",
  "author": "QuantFactory",
  "downloads": 363,
  "likes": 5,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 16
}