richarderkhov/r3dhummingbird_-_dialogpt-medium-joshua-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This is an instance of microsoft/DialoGPT-medium trained on a game character, Joshua from The World Ends With You. The data comes from a Kaggle game script dataset. I built a Discord AI chatbot based on this model. Check out my GitHub repo. Chat with the model: ``python from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained(\"r3dhummingbird/DialoGPT-medium-joshua\") model = AutoModelWithLMHead.from_pretrained(\"r3dhummingbird/DialoGPT-medium-joshua\") # Let's chat for 4 lines for step in range(4): # encode the new user input, add the eos_token and return a tensor in Pytorch new_user_input_ids = tokenizer.encode(input(\">> User:\") + tokenizer.eos_token, return_tensors='pt') # print(new_user_input_ids) # append the new user input tokens to the chat history bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids # generated a response while limiting the total chat history to 1000 tokens, chat_history_ids = model.generate( bot_input_ids, max_length=200, pad_token_id=tokenizer.eos_token_id, no_repeat_ngram_size=3, do_sample=True, top_k=100, top_p=0.7, temperature=0.8 ) # pretty print last ouput tokens from bot print(\"JoshuaBot: {}\".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True))) ``",
    "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\nDialoGPT-medium-joshua - GGUF\n- Model creator: https://huggingface.co/r3dhummingbird/\n- Original model: https://huggingface.co/r3dhummingbird/DialoGPT-medium-joshua/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [DialoGPT-medium-joshua.Q2_K.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q2_K.gguf) | Q2_K | 0.17GB |\n| [DialoGPT-medium-joshua.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.IQ3_XS.gguf) | IQ3_XS | 0.18GB |\n| [DialoGPT-medium-joshua.IQ3_S.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.IQ3_S.gguf) | IQ3_S | 0.19GB |\n| [DialoGPT-medium-joshua.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q3_K_S.gguf) | Q3_K_S | 0.19GB |\n| [DialoGPT-medium-joshua.IQ3_M.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.IQ3_M.gguf) | IQ3_M | 0.2GB |\n| [DialoGPT-medium-joshua.Q3_K.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q3_K.gguf) | Q3_K | 0.21GB |\n| [DialoGPT-medium-joshua.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q3_K_M.gguf) | Q3_K_M | 0.21GB |\n| [DialoGPT-medium-joshua.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q3_K_L.gguf) | Q3_K_L | 0.23GB |\n| [DialoGPT-medium-joshua.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.IQ4_XS.gguf) | IQ4_XS | 0.22GB |\n| [DialoGPT-medium-joshua.Q4_0.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q4_0.gguf) | Q4_0 | 0.23GB |\n| [DialoGPT-medium-joshua.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.IQ4_NL.gguf) | IQ4_NL | 0.23GB |\n| [DialoGPT-medium-joshua.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q4_K_S.gguf) | Q4_K_S | 0.23GB |\n| [DialoGPT-medium-joshua.Q4_K.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q4_K.gguf) | Q4_K | 0.25GB |\n| [DialoGPT-medium-joshua.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q4_K_M.gguf) | Q4_K_M | 0.25GB |\n| [DialoGPT-medium-joshua.Q4_1.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q4_1.gguf) | Q4_1 | 0.25GB |\n| [DialoGPT-medium-joshua.Q5_0.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q5_0.gguf) | Q5_0 | 0.27GB |\n| [DialoGPT-medium-joshua.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q5_K_S.gguf) | Q5_K_S | 0.27GB |\n| [DialoGPT-medium-joshua.Q5_K.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q5_K.gguf) | Q5_K | 0.29GB |\n| [DialoGPT-medium-joshua.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q5_K_M.gguf) | Q5_K_M | 0.29GB |\n| [DialoGPT-medium-joshua.Q5_1.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q5_1.gguf) | Q5_1 | 0.29GB |\n| [DialoGPT-medium-joshua.Q6_K.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q6_K.gguf) | Q6_K | 0.32GB |\n| [DialoGPT-medium-joshua.Q8_0.gguf](https://huggingface.co/RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf/blob/main/DialoGPT-medium-joshua.Q8_0.gguf) | Q8_0 | 0.41GB |\n\n\n\n\nOriginal model description:\n---\n\nthumbnail: https://raw.githubusercontent.com/RuolinZheng08/twewy-discord-chatbot/main/gif-demo/icon.png\n\ntags:\n\n- conversational\n\nlicense: mit\n\n---\n\n# DialoGPT Trained on the Speech of a Game Character\n\nThis is an instance of [microsoft/DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium) trained on a game character, Joshua from [The World Ends With You](https://en.wikipedia.org/wiki/The_World_Ends_with_You). The data comes from [a Kaggle game script dataset](https://www.kaggle.com/ruolinzheng/twewy-game-script).\n\nI built a Discord AI chatbot based on this model. [Check out my GitHub repo.](https://github.com/RuolinZheng08/twewy-discord-chatbot)\n\nChat with the model:\n\n```python\nfrom transformers import AutoTokenizer, AutoModelWithLMHead\n  \ntokenizer = AutoTokenizer.from_pretrained(\"r3dhummingbird/DialoGPT-medium-joshua\")\n\nmodel = AutoModelWithLMHead.from_pretrained(\"r3dhummingbird/DialoGPT-medium-joshua\")\n\n# Let's chat for 4 lines\nfor step in range(4):\n    # encode the new user input, add the eos_token and return a tensor in Pytorch\n    new_user_input_ids = tokenizer.encode(input(\">> User:\") + tokenizer.eos_token, return_tensors='pt')\n    # print(new_user_input_ids)\n\n    # append the new user input tokens to the chat history\n    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids\n\n    # generated a response while limiting the total chat history to 1000 tokens, \n    chat_history_ids = model.generate(\n        bot_input_ids, max_length=200,\n        pad_token_id=tokenizer.eos_token_id,  \n        no_repeat_ngram_size=3,       \n        do_sample=True, \n        top_k=100, \n        top_p=0.7,\n        temperature=0.8\n    )\n    \n    # pretty print last ouput tokens from bot\n    print(\"JoshuaBot: {}\".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 1022,
  "gated": false,
  "private": false,
  "last_modified": "2024-06-05T00:05:52.000Z",
  "created_at": "2024-06-04T23:32:25.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "665fa409d2ed9163a3948ce3",
  "id": "RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf",
  "modelId": "RichardErkhov/r3dhummingbird_-_DialoGPT-medium-joshua-gguf",
  "sha": "17fbf11113fe53fab1482f582fde2bef90609633",
  "createdAt": "2024-06-04T23:32:25.000Z",
  "lastModified": "2024-06-05T00:05:52.000Z",
  "author": "RichardErkhov",
  "downloads": 1022,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}