tsunemoto/heimer-ipo-tinyllama-1.1b-gguf overview

{
  "metadata": {},
  "card_data": {
    "title": "Heimer-ipo-TinyLlama-1.1B Quantized in GGUF",
    "tags": [
      "GGUF"
    ],
    "language": "en",
    "frontmatter": {
      "title": "\"Heimer-ipo-TinyLlama-1.1B Quantized in GGUF\"",
      "tags": [
        "GGUF"
      ],
      "language": "en"
    },
    "hero_image_url": "https://i.postimg.cc/MGwhtFfF/tsune-fixed.png",
    "summary": "This is a GGUF quantization of Heimer-ipo-TinyLlama-1.1B.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\ntitle: \"Heimer-ipo-TinyLlama-1.1B Quantized in GGUF\"\ntags:\n  - GGUF\nlanguage: en\n---\n![Image description](https://i.postimg.cc/MGwhtFfF/tsune-fixed.png)\n\n# Tsunemoto GGUF's of Heimer-ipo-TinyLlama-1.1B\n\nThis is a GGUF quantization of Heimer-ipo-TinyLlama-1.1B.\n\n## Original Repo Link:\n[Original Repository](https://huggingface.co/abideen/Heimer-ipo-TinyLlama-1.1B)\n\n## Original Model Card:\n---\n\n# Heimer-ipo-TinyLlama-1.1B\n\n\n![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/a7joKICVpqGElN3mh2MpS.jpeg)\n\n\n# WandB Experiment Tracking\n\nCheck out the experiment details in this [report](https://api.wandb.ai/links/zaiinn440/dqlt70dc)\n\n\n![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/HLhrSUFD1-e6f31F3WGK2.png)\n\n# 🧩 IPO adaptation hyperparameters\n\n## LoRA:\n\nr=8\n\nlora_alpha=16\n\nlora_dropout=0.05\n\nbias=\"none\"\n\ntask_type=\"CAUSAL_LM\"\n\ntarget_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']\n\n## Training arguments:\n\nper_device_train_batch_size=2\n\ngradient_accumulation_steps=4\n\ngradient_checkpointing=True\n\nlearning_rate=5e-5\n\nlr_scheduler_type=\"cosine\"\n\nmax_steps=50\n\noptim=\"paged_adamw_32bit\"\n\nwarmup_steps=10\n\n## DPOTrainer:\n\nbeta=0.1\n\nmax_prompt_length=1024\n\nmax_length=1536\n\nloss=\"ipo\"\n\n\n## 💻 Usage\n\nHere's a [Colab notebook](https://colab.research.google.com/drive/11KEX1LG3nRBoeGR0Iyy-459XllGlLOA9?usp=sharing) to run Heimer-TinyLLama-1.1B in 4-bit precision on a free T4 GPU.\n\n```python\n!pip install -qU transformers accelerate\n\nfrom transformers import AutoTokenizer\nimport transformers\nimport torch\n\nmodel = \"abideen/Heimer-ipo-TinyLlama-1.1B\"\nmessages = [{\"role\": \"user\", \"content\": \"Explain what is Data science.\"}]\n\ntokenizer = AutoTokenizer.from_pretrained(model)\nprompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)\npipeline = transformers.pipeline(\n    \"text-generation\",\n    model=model,\n    torch_dtype=torch.float16,\n    device_map=\"auto\",\n)\n\noutputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)\nprint(outputs[0][\"generated_text\"])\n```\n\n\"What is Data Science?\nA data scientist is an individual who has a passion for data and knowledge of the technology that can be used to help make sense of data. Data scientists are often involved in the development of new software and software platforms, as well as analyzing and interpreting data.\nWhat are the Important components of Data Science?\n1. Data: The data is the most important component of a data science project. Data science is the application of data science to make sense of data. Data scientists usually work with data, but data scientists are not necessarily data scientists.\n2. Analysis: This is the process of taking data and turning it into something useful.\n3. Modeling: The use of machine learning and statistical techniques.\n4. Prediction: The prediction of a future event, such as the future market share of a product or the future population of an area.\n5. Visualization: Displaying the data in a graphical or interactive format.\n6. Statistics: The use of statistical analysis techniques.\nWhat are the Advantages of Data Science?\nData science is the application of data science to make sense of data.\"",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "GGUF",
    "en",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 93,
  "gated": false,
  "private": false,
  "last_modified": "2024-01-15T14:35:25.000Z",
  "created_at": "2024-01-15T14:32:15.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "65a541efcb2c2799acba4a16",
  "id": "tsunemoto/Heimer-ipo-TinyLlama-1.1B-GGUF",
  "modelId": "tsunemoto/Heimer-ipo-TinyLlama-1.1B-GGUF",
  "sha": "8ab6428bfb994148a893d7e0b667b2decc8f87a3",
  "createdAt": "2024-01-15T14:32:15.000Z",
  "lastModified": "2024-01-15T14:35:25.000Z",
  "author": "tsunemoto",
  "downloads": 93,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 16
}