richarderkhov/maziyarpanahi_-_calme-2.1-qwen2-72b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "./qwen2-fine-tunes-maziyar-panahi.webp",
    "summary": "This model is a fine-tuned version of the powerful Qwen/Qwen2-72B-Instruct, pushing the boundaries of natural language understanding and generation even further. My goal was to create a versatile and robust model that excels across a wide range of benchmarks and real-world applications.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\ncalme-2.1-qwen2-72b - GGUF\n- Model creator: https://huggingface.co/MaziyarPanahi/\n- Original model: https://huggingface.co/MaziyarPanahi/calme-2.1-qwen2-72b/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [calme-2.1-qwen2-72b.Q2_K.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/blob/main/calme-2.1-qwen2-72b.Q2_K.gguf) | Q2_K | 27.76GB |\n| [calme-2.1-qwen2-72b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/blob/main/calme-2.1-qwen2-72b.IQ3_XS.gguf) | IQ3_XS | 30.58GB |\n| [calme-2.1-qwen2-72b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/blob/main/calme-2.1-qwen2-72b.IQ3_S.gguf) | IQ3_S | 32.12GB |\n| [calme-2.1-qwen2-72b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/blob/main/calme-2.1-qwen2-72b.Q3_K_S.gguf) | Q3_K_S | 32.12GB |\n| [calme-2.1-qwen2-72b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/blob/main/calme-2.1-qwen2-72b.IQ3_M.gguf) | IQ3_M | 33.06GB |\n| [calme-2.1-qwen2-72b.Q3_K.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/blob/main/calme-2.1-qwen2-72b.Q3_K.gguf) | Q3_K | 35.11GB |\n| [calme-2.1-qwen2-72b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/blob/main/calme-2.1-qwen2-72b.Q3_K_M.gguf) | Q3_K_M | 35.11GB |\n| [calme-2.1-qwen2-72b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/blob/main/calme-2.1-qwen2-72b.Q3_K_L.gguf) | Q3_K_L | 36.79GB |\n| [calme-2.1-qwen2-72b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | IQ4_XS | 37.4GB |\n| [calme-2.1-qwen2-72b.Q4_0.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q4_0 | 38.4GB |\n| [calme-2.1-qwen2-72b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | IQ4_NL | 38.9GB |\n| [calme-2.1-qwen2-72b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q4_K_S | 40.87GB |\n| [calme-2.1-qwen2-72b.Q4_K.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q4_K | 44.15GB |\n| [calme-2.1-qwen2-72b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q4_K_M | 44.15GB |\n| [calme-2.1-qwen2-72b.Q4_1.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q4_1 | 42.55GB |\n| [calme-2.1-qwen2-72b.Q5_0.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q5_0 | 46.71GB |\n| [calme-2.1-qwen2-72b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q5_K_S | 47.84GB |\n| [calme-2.1-qwen2-72b.Q5_K.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q5_K | 50.7GB |\n| [calme-2.1-qwen2-72b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q5_K_M | 50.7GB |\n| [calme-2.1-qwen2-72b.Q5_1.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q5_1 | 50.87GB |\n| [calme-2.1-qwen2-72b.Q6_K.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q6_K | 59.92GB |\n| [calme-2.1-qwen2-72b.Q8_0.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf/tree/main/) | Q8_0 | 71.95GB |\n\n\n\n\nOriginal model description:\n---\nlanguage:\n- en\nlicense: other\nlibrary_name: transformers\ntags:\n- chat\n- qwen\n- qwen2\n- finetune\n- chatml\nbase_model: Qwen/Qwen2-72B-Instruct\nlicense_name: tongyi-qianwen\nlicense_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE\npipeline_tag: text-generation\ninference: false\nmodel_creator: MaziyarPanahi\nquantized_by: MaziyarPanahi\nmodel-index:\n- name: calme-2.1-qwen2-72b\n  results:\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: IFEval (0-Shot)\n      type: HuggingFaceH4/ifeval\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: inst_level_strict_acc and prompt_level_strict_acc\n      value: 81.63\n      name: strict accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-72b\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: BBH (3-Shot)\n      type: BBH\n      args:\n        num_few_shot: 3\n    metrics:\n    - type: acc_norm\n      value: 57.33\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-72b\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MATH Lvl 5 (4-Shot)\n      type: hendrycks/competition_math\n      args:\n        num_few_shot: 4\n    metrics:\n    - type: exact_match\n      value: 36.03\n      name: exact match\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-72b\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: GPQA (0-shot)\n      type: Idavidrein/gpqa\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: acc_norm\n      value: 17.45\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-72b\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MuSR (0-shot)\n      type: TAUR-Lab/MuSR\n      args:\n        num_few_shot: 0\n    metrics:\n    - type: acc_norm\n      value: 20.15\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-72b\n      name: Open LLM Leaderboard\n  - task:\n      type: text-generation\n      name: Text Generation\n    dataset:\n      name: MMLU-PRO (5-shot)\n      type: TIGER-Lab/MMLU-Pro\n      config: main\n      split: test\n      args:\n        num_few_shot: 5\n    metrics:\n    - type: acc\n      value: 49.05\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-72b\n      name: Open LLM Leaderboard\n---\n\n<img src=\"./qwen2-fine-tunes-maziyar-panahi.webp\" alt=\"Qwen2 fine-tune\" width=\"800\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>\n\n# MaziyarPanahi/calme-2.1-qwen2-72b\n\nThis model is a fine-tuned version of the powerful `Qwen/Qwen2-72B-Instruct`, pushing the boundaries of natural language understanding and generation even further. My goal was to create a versatile and robust model that excels across a wide range of benchmarks and real-world applications.\n\n## Use Cases\n\nThis model is suitable for a wide range of applications, including but not limited to:\n\n- Advanced question-answering systems\n- Intelligent chatbots and virtual assistants\n- Content generation and summarization\n- Code generation and analysis\n- Complex problem-solving and decision support\n\n# ⚡ Quantized GGUF\n\nAll GGUF models are available here: [MaziyarPanahi/calme-2.1-qwen2-72b-GGUF](https://huggingface.co/MaziyarPanahi/calme-2.1-qwen2-72b-GGUF)\n\n# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)\n\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__calme-2.1-qwen2-72b)\n\n|      Metric       |Value|\n|-------------------|----:|\n|Avg.               |43.61|\n|IFEval (0-Shot)    |81.63|\n|BBH (3-Shot)       |57.33|\n|MATH Lvl 5 (4-Shot)|36.03|\n|GPQA (0-shot)      |17.45|\n|MuSR (0-shot)      |20.15|\n|MMLU-PRO (5-shot)  |49.05|\n\n\n\n|    Tasks     |Version|Filter|n-shot|Metric|Value |   |Stderr|\n|--------------|------:|------|-----:|------|-----:|---|-----:|\n|truthfulqa_mc2|      2|none  |     0|acc   |0.6761|±  |0.0148|\n\n|  Tasks   |Version|Filter|n-shot|Metric|Value |   |Stderr|\n|----------|------:|------|-----:|------|-----:|---|-----:|\n|winogrande|      1|none  |     5|acc   |0.8248|±  |0.0107|\n\n|    Tasks    |Version|Filter|n-shot| Metric |Value |   |Stderr|\n|-------------|------:|------|-----:|--------|-----:|---|-----:|\n|arc_challenge|      1|none  |    25|acc     |0.6852|±  |0.0136|\n|             |       |none  |    25|acc_norm|0.7184|±  |0.0131|\n\n|Tasks|Version|     Filter     |n-shot|  Metric   |Value |   |Stderr|\n|-----|------:|----------------|-----:|-----------|-----:|---|-----:|\n|gsm8k|      3|strict-match    |     5|exact_match|0.8582|±  |0.0096|\n|     |       |flexible-extract|     5|exact_match|0.8893|±  |0.0086|\n\n# Prompt Template\n\nThis model uses `ChatML` prompt template:\n\n```\n<|im_start|>system\n{System}\n<|im_end|>\n<|im_start|>user\n{User}\n<|im_end|>\n<|im_start|>assistant\n{Assistant}\n````\n\n# How to use\n\n\n```python\n\n# Use a pipeline as a high-level helper\n\nfrom transformers import pipeline\n\nmessages = [\n    {\"role\": \"user\", \"content\": \"Who are you?\"},\n]\npipe = pipeline(\"text-generation\", model=\"MaziyarPanahi/calme-2.1-qwen2-72b\")\npipe(messages)\n\n\n# Load model directly\n\nfrom transformers import AutoTokenizer, AutoModelForCausalLM\n\ntokenizer = AutoTokenizer.from_pretrained(\"MaziyarPanahi/calme-2.1-qwen2-72b\")\nmodel = AutoModelForCausalLM.from_pretrained(\"MaziyarPanahi/calme-2.1-qwen2-72b\")\n```\n\n# Ethical Considerations\n\nAs with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 86,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-10T09:52:14.000Z",
  "created_at": "2024-10-09T06:58:26.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67062992e343e345b77d0734",
  "id": "RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf",
  "modelId": "RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-72b-gguf",
  "sha": "eb9b2e1975defc5babe32f14572ca74c6a00cb6f",
  "createdAt": "2024-10-09T06:58:26.000Z",
  "lastModified": "2024-10-10T09:52:14.000Z",
  "author": "RichardErkhov",
  "downloads": 86,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 37
}