richarderkhov/sawao_-_gemma2-2b-sft-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "base_model: gemma2_2b gemma2 27bにより生成したself instructデータ10kによりinstrution tuningを実施",
    "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\ngemma2-2b-sft - GGUF\n- Model creator: https://huggingface.co/sawao/\n- Original model: https://huggingface.co/sawao/gemma2-2b-sft/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [gemma2-2b-sft.Q2_K.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q2_K.gguf) | Q2_K | 1.15GB |\n| [gemma2-2b-sft.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.IQ3_XS.gguf) | IQ3_XS | 1.22GB |\n| [gemma2-2b-sft.IQ3_S.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.IQ3_S.gguf) | IQ3_S | 1.27GB |\n| [gemma2-2b-sft.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q3_K_S.gguf) | Q3_K_S | 1.27GB |\n| [gemma2-2b-sft.IQ3_M.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.IQ3_M.gguf) | IQ3_M | 1.3GB |\n| [gemma2-2b-sft.Q3_K.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q3_K.gguf) | Q3_K | 1.36GB |\n| [gemma2-2b-sft.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q3_K_M.gguf) | Q3_K_M | 1.36GB |\n| [gemma2-2b-sft.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q3_K_L.gguf) | Q3_K_L | 1.44GB |\n| [gemma2-2b-sft.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.IQ4_XS.gguf) | IQ4_XS | 1.47GB |\n| [gemma2-2b-sft.Q4_0.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q4_0.gguf) | Q4_0 | 1.52GB |\n| [gemma2-2b-sft.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.IQ4_NL.gguf) | IQ4_NL | 1.53GB |\n| [gemma2-2b-sft.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q4_K_S.gguf) | Q4_K_S | 1.53GB |\n| [gemma2-2b-sft.Q4_K.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q4_K.gguf) | Q4_K | 1.59GB |\n| [gemma2-2b-sft.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q4_K_M.gguf) | Q4_K_M | 1.59GB |\n| [gemma2-2b-sft.Q4_1.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q4_1.gguf) | Q4_1 | 1.64GB |\n| [gemma2-2b-sft.Q5_0.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q5_0.gguf) | Q5_0 | 1.75GB |\n| [gemma2-2b-sft.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q5_K_S.gguf) | Q5_K_S | 1.75GB |\n| [gemma2-2b-sft.Q5_K.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q5_K.gguf) | Q5_K | 1.79GB |\n| [gemma2-2b-sft.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q5_K_M.gguf) | Q5_K_M | 1.79GB |\n| [gemma2-2b-sft.Q5_1.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q5_1.gguf) | Q5_1 | 1.87GB |\n| [gemma2-2b-sft.Q6_K.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q6_K.gguf) | Q6_K | 2.0GB |\n| [gemma2-2b-sft.Q8_0.gguf](https://huggingface.co/RichardErkhov/sawao_-_gemma2-2b-sft-gguf/blob/main/gemma2-2b-sft.Q8_0.gguf) | Q8_0 | 2.59GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\ntags: []\n---\n\n# gemma2-2b-sft\nbase_model: gemma2_2b\ngemma2 27bにより生成したself instructデータ10kによりinstrution tuningを実施\n\n## Eval\nelyza-task-100\n\n## Use\n```\nmodel = AutoModelForCausalLM.from_pretrained(\n            model_name,\n            torch_dtype=torch.bfloat16,\n            device_map=\"auto\"  # GPU自動割り当て\n        )\n\ntokenizer = AutoTokenizer.from_pretrained(model_name)\n\nmessages_list = [\n  [\n    {\"role\": \"user\", \"content\": \"仕事の熱意を取り戻すためのアイデアを5つ挙げてください。\"}\n  ]\n]\n\nprompts = [self.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) for messages in messages_list]\n        \ninputs = self.tokenizer(prompts, return_tensors=\"pt\", padding=True).to(self.model.device)\n\noutputs = self.model.generate(\n    **inputs,\n    temperature=self.generate_configs[\"temperature\"],\n    max_new_tokens=self.generate_configs[\"max_new_tokens\"],\n    top_p=self.generate_configs[\"top_p\"],\n    top_k=self.generate_configs[\"top_k\"],\n    repetition_penalty=self.generate_configs[\"repetition_penalty\"],\n    pad_token_id=self.tokenizer.pad_token_id,\n    eos_token_id=self.tokenizer.eos_token_id,\n)\n\nprint(outputs)\n\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 466,
  "gated": false,
  "private": false,
  "last_modified": "2025-02-26T10:10:32.000Z",
  "created_at": "2025-02-26T07:44:04.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67bec64487e945a9f4ef883c",
  "id": "RichardErkhov/sawao_-_gemma2-2b-sft-gguf",
  "modelId": "RichardErkhov/sawao_-_gemma2-2b-sft-gguf",
  "sha": "69f8d76a483d019d14bda048347d392bde6c6247",
  "createdAt": "2025-02-26T07:44:04.000Z",
  "lastModified": "2025-02-26T10:10:32.000Z",
  "author": "RichardErkhov",
  "downloads": 466,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}