richarderkhov/maziyarpanahi_-_calme-2.1-qwen2-7b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "./qwen2-fine-tunes-maziyar-panahi.webp",
    "summary": "This is a fine-tuned version of the Qwen/Qwen2-7B model. It aims to improve the base model across all benchmarks. # ⚡ Quantized GGUF All GGUF models are available here: MaziyarPanahi/calme-2.1-qwen2-7b # 🏆 Open LLM Leaderboard Evaluation Results Detailed results can be found here |      Metric       |Value| |-------------------|----:| |Avg.               |23.20| |IFEval (0-Shot)    |38.16| |BBH (3-Shot)       |31.01| |MATH Lvl 5 (4-Shot)|21.07| |GPQA (0-shot)      | 5.26| |MuSR (0-shot)      |13.80| |MMLU-PRO (5-shot)  |29.92| # Prompt Template This model uses ChatML prompt template: `` system {System}  user {User}  assistant {Assistant} `` # How to use `python # Use a pipeline as a high-level helper from transformers import pipeline messages = [ {\"role\": \"user\", \"content\": \"Who are you?\"}, ] pipe = pipeline(\"text-generation\", model=\"MaziyarPanahi/calme-2.1-qwen2-7b\") pipe(messages) # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained(\"MaziyarPanahi/calme-2.1-qwen2-7b\") model = AutoModelForCausalLM.from_pretrained(\"MaziyarPanahi/calme-2.1-qwen2-7b\") ``",
    "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-qwen2-7b - GGUF\n- Model creator: https://huggingface.co/MaziyarPanahi/\n- Original model: https://huggingface.co/MaziyarPanahi/calme-2.1-qwen2-7b/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [calme-2.1-qwen2-7b.Q2_K.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q2_K.gguf) | Q2_K | 2.81GB |\n| [calme-2.1-qwen2-7b.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.IQ3_XS.gguf) | IQ3_XS | 3.12GB |\n| [calme-2.1-qwen2-7b.IQ3_S.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.IQ3_S.gguf) | IQ3_S | 3.26GB |\n| [calme-2.1-qwen2-7b.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q3_K_S.gguf) | Q3_K_S | 3.25GB |\n| [calme-2.1-qwen2-7b.IQ3_M.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.IQ3_M.gguf) | IQ3_M | 3.33GB |\n| [calme-2.1-qwen2-7b.Q3_K.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q3_K.gguf) | Q3_K | 3.55GB |\n| [calme-2.1-qwen2-7b.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q3_K_M.gguf) | Q3_K_M | 3.55GB |\n| [calme-2.1-qwen2-7b.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q3_K_L.gguf) | Q3_K_L | 3.81GB |\n| [calme-2.1-qwen2-7b.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.IQ4_XS.gguf) | IQ4_XS | 3.96GB |\n| [calme-2.1-qwen2-7b.Q4_0.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q4_0.gguf) | Q4_0 | 4.13GB |\n| [calme-2.1-qwen2-7b.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.IQ4_NL.gguf) | IQ4_NL | 4.16GB |\n| [calme-2.1-qwen2-7b.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q4_K_S.gguf) | Q4_K_S | 4.15GB |\n| [calme-2.1-qwen2-7b.Q4_K.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q4_K.gguf) | Q4_K | 4.36GB |\n| [calme-2.1-qwen2-7b.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q4_K_M.gguf) | Q4_K_M | 4.36GB |\n| [calme-2.1-qwen2-7b.Q4_1.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q4_1.gguf) | Q4_1 | 4.54GB |\n| [calme-2.1-qwen2-7b.Q5_0.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q5_0.gguf) | Q5_0 | 4.95GB |\n| [calme-2.1-qwen2-7b.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q5_K_S.gguf) | Q5_K_S | 4.95GB |\n| [calme-2.1-qwen2-7b.Q5_K.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q5_K.gguf) | Q5_K | 5.07GB |\n| [calme-2.1-qwen2-7b.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q5_K_M.gguf) | Q5_K_M | 5.07GB |\n| [calme-2.1-qwen2-7b.Q5_1.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q5_1.gguf) | Q5_1 | 5.36GB |\n| [calme-2.1-qwen2-7b.Q6_K.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q6_K.gguf) | Q6_K | 5.82GB |\n| [calme-2.1-qwen2-7b.Q8_0.gguf](https://huggingface.co/RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf/blob/main/calme-2.1-qwen2-7b.Q8_0.gguf) | Q8_0 | 7.54GB |\n\n\n\n\nOriginal model description:\n---\nlanguage:\n- en\nlicense: apache-2.0\nlibrary_name: transformers\ntags:\n- chat\n- qwen\n- qwen2\n- finetune\n- chatml\n- OpenHermes-2.5\n- HelpSteer2\n- Orca\n- SlimOrca\nbase_model: Qwen/Qwen2-7B\ndatasets:\n- nvidia/HelpSteer2\n- teknium/OpenHermes-2.5\n- microsoft/orca-math-word-problems-200k\n- Open-Orca/SlimOrca\nmodel_name: calme-2.1-qwen2-7b\npipeline_tag: text-generation\ninference: false\nmodel_creator: MaziyarPanahi\nquantized_by: MaziyarPanahi\nmodel-index:\n- name: calme-2.1-qwen2-7b\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: 38.16\n      name: strict accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-7b\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: 31.01\n      name: normalized accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-7b\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: 21.07\n      name: exact match\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-7b\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: 5.26\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-7b\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: 13.8\n      name: acc_norm\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-7b\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: 29.92\n      name: accuracy\n    source:\n      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-2.1-qwen2-7b\n      name: Open LLM Leaderboard\n---\n\n<img src=\"./qwen2-fine-tunes-maziyar-panahi.webp\" alt=\"Qwen2 fine-tune\" width=\"500\" style=\"margin-left:'auto' margin-right:'auto' display:'block'\"/>\n\n# MaziyarPanahi/calme-2.1-qwen2-7b\n\nThis is a fine-tuned version of the `Qwen/Qwen2-7B` model. It aims to improve the base model across all benchmarks.\n\n# ⚡ Quantized GGUF\n\nAll GGUF models are available here: [MaziyarPanahi/calme-2.1-qwen2-7b](https://huggingface.co/MaziyarPanahi/calme-2.1-qwen2-7b)\n\n# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__calme-2.1-qwen2-7b)\n\n|      Metric       |Value|\n|-------------------|----:|\n|Avg.               |23.20|\n|IFEval (0-Shot)    |38.16|\n|BBH (3-Shot)       |31.01|\n|MATH Lvl 5 (4-Shot)|21.07|\n|GPQA (0-shot)      | 5.26|\n|MuSR (0-shot)      |13.80|\n|MMLU-PRO (5-shot)  |29.92|\n\n\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-qwen2-7b\")\npipe(messages)\n\n\n# Load model directly\n\nfrom transformers import AutoTokenizer, AutoModelForCausalLM\n\ntokenizer = AutoTokenizer.from_pretrained(\"MaziyarPanahi/calme-2.1-qwen2-7b\")\nmodel = AutoModelForCausalLM.from_pretrained(\"MaziyarPanahi/calme-2.1-qwen2-7b\")\n```\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 406,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-20T11:58:53.000Z",
  "created_at": "2024-09-20T08:37:24.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66ed3444d98870c2e6c8e90d",
  "id": "RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf",
  "modelId": "RichardErkhov/MaziyarPanahi_-_calme-2.1-qwen2-7b-gguf",
  "sha": "28be83faf3818458ce45d3d7ffcdcb7780368e35",
  "createdAt": "2024-09-20T08:37:24.000Z",
  "lastModified": "2024-09-20T11:58:53.000Z",
  "author": "RichardErkhov",
  "downloads": 406,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}