richarderkhov/huihui-ai_-_qwen2.5-32b-instruct-abliterated-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This is an uncensored version of Qwen2.5-32B-Instruct created with abliteration (see this article to know more about it). Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.",
    "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\nQwen2.5-32B-Instruct-abliterated - GGUF\n- Model creator: https://huggingface.co/huihui-ai/\n- Original model: https://huggingface.co/huihui-ai/Qwen2.5-32B-Instruct-abliterated/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Qwen2.5-32B-Instruct-abliterated.Q2_K.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q2_K.gguf) | Q2_K | 11.47GB |\n| [Qwen2.5-32B-Instruct-abliterated.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.IQ3_XS.gguf) | IQ3_XS | 12.76GB |\n| [Qwen2.5-32B-Instruct-abliterated.IQ3_S.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.IQ3_S.gguf) | IQ3_S | 13.45GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q3_K_S.gguf) | Q3_K_S | 13.4GB |\n| [Qwen2.5-32B-Instruct-abliterated.IQ3_M.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.IQ3_M.gguf) | IQ3_M | 13.79GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q3_K.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q3_K.gguf) | Q3_K | 14.84GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q3_K_M.gguf) | Q3_K_M | 14.84GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q3_K_L.gguf) | Q3_K_L | 16.06GB |\n| [Qwen2.5-32B-Instruct-abliterated.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.IQ4_XS.gguf) | IQ4_XS | 16.64GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q4_0.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q4_0.gguf) | Q4_0 | 17.36GB |\n| [Qwen2.5-32B-Instruct-abliterated.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.IQ4_NL.gguf) | IQ4_NL | 17.53GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q4_K_S.gguf) | Q4_K_S | 17.49GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q4_K.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q4_K.gguf) | Q4_K | 18.49GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q4_K_M.gguf) | Q4_K_M | 18.49GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q4_1.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q4_1.gguf) | Q4_1 | 19.22GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q5_0.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q5_0.gguf) | Q5_0 | 21.08GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q5_K_S.gguf) | Q5_K_S | 21.08GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q5_K.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q5_K.gguf) | Q5_K | 21.66GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q5_K_M.gguf) | Q5_K_M | 21.66GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q5_1.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q5_1.gguf) | Q5_1 | 22.95GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q6_K.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q6_K.gguf) | Q6_K | 25.04GB |\n| [Qwen2.5-32B-Instruct-abliterated.Q8_0.gguf](https://huggingface.co/RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf/blob/main/Qwen2.5-32B-Instruct-abliterated.Q8_0.gguf) | Q8_0 | 32.43GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: apache-2.0\nlicense_link: https://huggingface.co/huihui-ai/Qwen2.5-32B-Instruct-abliterated/blob/main/LICENSE\nlanguage:\n- en\npipeline_tag: text-generation\nbase_model: Qwen/Qwen2.5-32B-Instruct\ntags:\n- chat\n- abliterated\n- uncensored\n---\n\n# huihui-ai/Qwen2.5-32B-Instruct-abliterated\n\n\nThis is an uncensored version of [Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it).\n\nSpecial thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models.\n\n## Usage\nYou can use this model in your applications by loading it with Hugging Face's `transformers` library:\n\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\n# Load the model and tokenizer\nmodel_name = \"huihui-ai/Qwen2.5-32B-Instruct-abliterated\"\nmodel = AutoModelForCausalLM.from_pretrained(\n    model_name,\n    torch_dtype=\"auto\",\n    device_map=\"auto\"\n)\ntokenizer = AutoTokenizer.from_pretrained(model_name)\n\n# Initialize conversation context\ninitial_messages = [\n    {\"role\": \"system\", \"content\": \"You are Qwen, created by Alibaba Cloud. You are a helpful assistant.\"}\n]\nmessages = initial_messages.copy()  # Copy the initial conversation context\n\n# Enter conversation loop\nwhile True:\n    # Get user input\n    user_input = input(\"User: \").strip()  # Strip leading and trailing spaces\n\n    # If the user types '/exit', end the conversation\n    if user_input.lower() == \"/exit\":\n        print(\"Exiting chat.\")\n        break\n\n    # If the user types '/clean', reset the conversation context\n    if user_input.lower() == \"/clean\":\n        messages = initial_messages.copy()  # Reset conversation context\n        print(\"Chat history cleared. Starting a new conversation.\")\n        continue\n\n    # If input is empty, prompt the user and continue\n    if not user_input:\n        print(\"Input cannot be empty. Please enter something.\")\n        continue\n\n    # Add user input to the conversation\n    messages.append({\"role\": \"user\", \"content\": user_input})\n\n    # Build the chat template\n    text = tokenizer.apply_chat_template(\n        messages,\n        tokenize=False,\n        add_generation_prompt=True\n    )\n\n    # Tokenize input and prepare it for the model\n    model_inputs = tokenizer([text], return_tensors=\"pt\").to(model.device)\n\n    # Generate a response from the model\n    generated_ids = model.generate(\n        **model_inputs,\n        max_new_tokens=8192\n    )\n\n    # Extract model output, removing special tokens\n    generated_ids = [\n        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)\n    ]\n    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]\n\n    # Add the model's response to the conversation\n    messages.append({\"role\": \"assistant\", \"content\": response})\n\n    # Print the model's response\n    print(f\"Qwen: {response}\")\n\n```\n\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 595,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-17T03:24:19.000Z",
  "created_at": "2024-10-16T13:50:20.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "670fc49c1cbc3c503cb73b67",
  "id": "RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf",
  "modelId": "RichardErkhov/huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf",
  "sha": "b21a35d1dfeea083252ad7ca87bfab320c8c8b39",
  "createdAt": "2024-10-16T13:50:20.000Z",
  "lastModified": "2024-10-17T03:24:19.000Z",
  "author": "RichardErkhov",
  "downloads": 595,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}