richarderkhov/kendamarron_-_tokara-0.5b-v0.1-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models Tokara-0.5B-v0.1 - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | Tokara-0.5B-v0.1.Q2_K.gguf | Q2_K | 0.23GB | | Tokara-0.5B-v0.1.IQ3_XS.gguf | IQ3_XS | 0.24GB | | Tokara-0.5B-v0.1.IQ3_S.gguf | IQ3_S | 0.25GB | | Tokara-0.5B-v0.1.Q3_K_S.gguf | Q3_K_S | 0.25GB | | Tokara-0.5B-v0.1.IQ3_M.gguf | IQ3_M | 0.26GB | | Tokara-0.5B-v0.1.Q3_K.gguf | Q3_K | 0.26GB | | Tokara-0.5B-v0.1.Q3_K_M.gguf | Q3_K_M | 0.26GB | | Tokara-0.5B-v0.1.Q3_K_L.gguf | Q3_K_L | 0.28GB | | Tokara-0.5B-v0.1.IQ4_XS.gguf | IQ4_XS | 0.28GB | | Tokara-0.5B-v0.1.Q4_0.gguf | Q4_0 | 0.29GB | | Tokara-0.5B-v0.1.IQ4_NL.gguf | IQ4_NL | 0.29GB | | Tokara-0.5B-v0.1.Q4_K_S.gguf | Q4_K_S | 0.29GB | | Tokara-0.5B-v0.1.Q4_K.gguf | Q4_K | 0.3GB | | Tokara-0.5B-v0.1.Q4_K_M.gguf | Q4_K_M | 0.3GB | | Tokara-0.5B-v0.1.Q4_1.gguf | Q4_1 | 0.3GB | | Tokara-0.5B-v0.1.Q5_0.gguf | Q5_0 | 0.32GB | | Tokara-0.5B-v0.1.Q5_K_S.gguf | Q5_K_S | 0.32GB | | Tokara-0.5B-v0.1.Q5_K.gguf | Q5_K | 0.33GB | | Tokara-0.5B-v0.1.Q5_K_M.gguf | Q5_K_M | 0.33GB | | Tokara-0.5B-v0.1.Q5_1.gguf | Q5_1 | 0.34GB | | Tokara-0.5B-v0.1.Q6_K.gguf | Q6_K | 0.36GB | | Tokara-0.5B-v0.1.Q8_0.gguf | Q8_0 | 0.47GB | Original model description: --- license: other license_name: tongyi-qianwen-research license_link: https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE language: pipeline_tag: text-generation datasets: ---",
    "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\nTokara-0.5B-v0.1 - GGUF\n- Model creator: https://huggingface.co/Kendamarron/\n- Original model: https://huggingface.co/Kendamarron/Tokara-0.5B-v0.1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Tokara-0.5B-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q2_K.gguf) | Q2_K | 0.23GB |\n| [Tokara-0.5B-v0.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.IQ3_XS.gguf) | IQ3_XS | 0.24GB |\n| [Tokara-0.5B-v0.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.IQ3_S.gguf) | IQ3_S | 0.25GB |\n| [Tokara-0.5B-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q3_K_S.gguf) | Q3_K_S | 0.25GB |\n| [Tokara-0.5B-v0.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.IQ3_M.gguf) | IQ3_M | 0.26GB |\n| [Tokara-0.5B-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q3_K.gguf) | Q3_K | 0.26GB |\n| [Tokara-0.5B-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q3_K_M.gguf) | Q3_K_M | 0.26GB |\n| [Tokara-0.5B-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q3_K_L.gguf) | Q3_K_L | 0.28GB |\n| [Tokara-0.5B-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.IQ4_XS.gguf) | IQ4_XS | 0.28GB |\n| [Tokara-0.5B-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q4_0.gguf) | Q4_0 | 0.29GB |\n| [Tokara-0.5B-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.IQ4_NL.gguf) | IQ4_NL | 0.29GB |\n| [Tokara-0.5B-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q4_K_S.gguf) | Q4_K_S | 0.29GB |\n| [Tokara-0.5B-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q4_K.gguf) | Q4_K | 0.3GB |\n| [Tokara-0.5B-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q4_K_M.gguf) | Q4_K_M | 0.3GB |\n| [Tokara-0.5B-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q4_1.gguf) | Q4_1 | 0.3GB |\n| [Tokara-0.5B-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q5_0.gguf) | Q5_0 | 0.32GB |\n| [Tokara-0.5B-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q5_K_S.gguf) | Q5_K_S | 0.32GB |\n| [Tokara-0.5B-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q5_K.gguf) | Q5_K | 0.33GB |\n| [Tokara-0.5B-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q5_K_M.gguf) | Q5_K_M | 0.33GB |\n| [Tokara-0.5B-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q5_1.gguf) | Q5_1 | 0.34GB |\n| [Tokara-0.5B-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q6_K.gguf) | Q6_K | 0.36GB |\n| [Tokara-0.5B-v0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf/blob/main/Tokara-0.5B-v0.1.Q8_0.gguf) | Q8_0 | 0.47GB |\n\n\n\n\nOriginal model description:\n---\nlicense: other\nlicense_name: tongyi-qianwen-research\nlicense_link: https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE\nlanguage:\n- ja\n- en\npipeline_tag: text-generation\ndatasets:\n- izumi-lab/wikipedia-ja-20230720\n- oscar-corpus/OSCAR-2301\n- aixsatoshi/cosmopedia-japanese-100k\n- BEE-spoke-data/wikipedia-20230901.en-deduped\n---\n\n## モデルについて\n[Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)を日英データ5Bトークンで継続事前学習したモデルです。\n\nベンチマークのスコアは低下していますが、ベースモデルよりも安定して日本語を出力するようになっています。\n\n詳細は[こちら](https://zenn.dev/kendama/articles/55564e12da6e82)をご覧ください。\n\n## ベンチマーク\n[Stability-AI/lm-evaluation-harness](https://github.com/Stability-AI/lm-evaluation-harness)の3項目で評価\n| モデル                       | jsquad(1-shot) | jcommonsenseqa(1-shot) | jnli(1-shot) | \n| ---------------------------- | -------------- | ---------------------- | ------------ | \n| Kendamarron/Tokara-0.5B-v0.1 | 26.4295        | 0.2663                 | 0.5509       | \n| Qwen/Qwen1.5-0.5B            | 31.3597        | 0.2556                 | 0.5534       | \n\n## 名前について\n日本の在来馬であるトカラ馬から\n\n```python\nfrom transformers import AutoTokenizer, AutoModelForCausalLM, pipeline\n\nmodel = AutoModelForCausalLM.from_pretrained('Kendamarron/Tokara-0.5B-v0.1')\ntokenizer = AutoTokenizer.from_pretrained('Kendamarron/Tokara-0.5B-v0.1')\n\npipe = pipeline('text-generation', model=model, tokenizer=tokenizer)\n\nprompt = \"大規模言語モデルとは、\"\n\nprint(pipe(prompt, max_length=128, repetition_penalty=1.1, temperature=0.7, top_p=0.95))\n\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 244,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-18T03:51:15.000Z",
  "created_at": "2024-07-18T03:43:19.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66988f5724de09d10ce5dcd4",
  "id": "RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf",
  "modelId": "RichardErkhov/Kendamarron_-_Tokara-0.5B-v0.1-gguf",
  "sha": "7d7031588fa1a4b6fe6510ec838e643d291a2c51",
  "createdAt": "2024-07-18T03:43:19.000Z",
  "lastModified": "2024-07-18T03:51:15.000Z",
  "author": "RichardErkhov",
  "downloads": 244,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}