richarderkhov/toastloaf_-_gpt2-magpie-ultra-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model was trained using AutoTrain. For more information, please visit AutoTrain. # Usage ``python from transformers import AutoModelForCausalLM, AutoTokenizer model_path = \"PATH_TO_THIS_REPO\" tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained( model_path, device_map=\"auto\", torch_dtype='auto' ).eval() # Prompt content: \"hi\" messages = [ {\"role\": \"user\", \"content\": \"hi\"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True) # Model response: \"Hello! How can I assist you today?\" print(response) ``",
    "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\ngpt2-magpie-ultra - GGUF\n- Model creator: https://huggingface.co/toastloaf/\n- Original model: https://huggingface.co/toastloaf/gpt2-magpie-ultra/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [gpt2-magpie-ultra.Q2_K.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q2_K.gguf) | Q2_K | 0.08GB |\n| [gpt2-magpie-ultra.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.IQ3_XS.gguf) | IQ3_XS | 0.08GB |\n| [gpt2-magpie-ultra.IQ3_S.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.IQ3_S.gguf) | IQ3_S | 0.08GB |\n| [gpt2-magpie-ultra.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q3_K_S.gguf) | Q3_K_S | 0.08GB |\n| [gpt2-magpie-ultra.IQ3_M.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.IQ3_M.gguf) | IQ3_M | 0.09GB |\n| [gpt2-magpie-ultra.Q3_K.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q3_K.gguf) | Q3_K | 0.09GB |\n| [gpt2-magpie-ultra.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q3_K_M.gguf) | Q3_K_M | 0.09GB |\n| [gpt2-magpie-ultra.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q3_K_L.gguf) | Q3_K_L | 0.1GB |\n| [gpt2-magpie-ultra.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.IQ4_XS.gguf) | IQ4_XS | 0.1GB |\n| [gpt2-magpie-ultra.Q4_0.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q4_0.gguf) | Q4_0 | 0.1GB |\n| [gpt2-magpie-ultra.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.IQ4_NL.gguf) | IQ4_NL | 0.1GB |\n| [gpt2-magpie-ultra.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q4_K_S.gguf) | Q4_K_S | 0.1GB |\n| [gpt2-magpie-ultra.Q4_K.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q4_K.gguf) | Q4_K | 0.11GB |\n| [gpt2-magpie-ultra.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q4_K_M.gguf) | Q4_K_M | 0.11GB |\n| [gpt2-magpie-ultra.Q4_1.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q4_1.gguf) | Q4_1 | 0.11GB |\n| [gpt2-magpie-ultra.Q5_0.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q5_0.gguf) | Q5_0 | 0.11GB |\n| [gpt2-magpie-ultra.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q5_K_S.gguf) | Q5_K_S | 0.11GB |\n| [gpt2-magpie-ultra.Q5_K.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q5_K.gguf) | Q5_K | 0.12GB |\n| [gpt2-magpie-ultra.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q5_K_M.gguf) | Q5_K_M | 0.12GB |\n| [gpt2-magpie-ultra.Q5_1.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q5_1.gguf) | Q5_1 | 0.12GB |\n| [gpt2-magpie-ultra.Q6_K.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q6_K.gguf) | Q6_K | 0.13GB |\n| [gpt2-magpie-ultra.Q8_0.gguf](https://huggingface.co/RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf/blob/main/gpt2-magpie-ultra.Q8_0.gguf) | Q8_0 | 0.17GB |\n\n\n\n\nOriginal model description:\n---\ntags:\n- autotrain\n- text-generation-inference\n- text-generation\nlibrary_name: transformers\nbase_model: openai-community/gpt2\nwidget:\n  - messages:\n      - role: user\n        content: What is your favorite condiment?\nlicense: other\ndatasets:\n- argilla/magpie-ultra-v0.1\n---\n\n# Model Trained Using AutoTrain\n\nThis model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).\n\n# Usage\n\n```python\n\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\nmodel_path = \"PATH_TO_THIS_REPO\"\n\ntokenizer = AutoTokenizer.from_pretrained(model_path)\nmodel = AutoModelForCausalLM.from_pretrained(\n    model_path,\n    device_map=\"auto\",\n    torch_dtype='auto'\n).eval()\n\n# Prompt content: \"hi\"\nmessages = [\n    {\"role\": \"user\", \"content\": \"hi\"}\n]\n\ninput_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')\noutput_ids = model.generate(input_ids.to('cuda'))\nresponse = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)\n\n# Model response: \"Hello! How can I assist you today?\"\nprint(response)\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 167,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-01T22:30:07.000Z",
  "created_at": "2025-03-01T22:27:05.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67c389b9546e6c74c7fd1e2c",
  "id": "RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf",
  "modelId": "RichardErkhov/toastloaf_-_gpt2-magpie-ultra-gguf",
  "sha": "e04e56940956f1da6b96ed65ac77144b97ce2b82",
  "createdAt": "2025-03-01T22:27:05.000Z",
  "lastModified": "2025-03-01T22:30:07.000Z",
  "author": "RichardErkhov",
  "downloads": 167,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}