gguf-a-lot/deephat-v1-7b-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "frontmatter": {
      "license": "apache-2.0"
    },
    "hero_image_url": "https://huggingface.co/spaces/GGUF-A-Lot/README/resolve/main/DeepHat-V1-7B.png",
    "summary": "Join us on Discord # Technical Overview DeepHat is a finetune of Qwen2.5-Coder-7B, and inherits the following features:",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\n---\n<style>\na.magic-link {\n  color: #2a4db0;\n  text-decoration: none;\n  font-weight: bold;\n  transition: all 0.3s ease;\n}\n\na.magic-link:hover {\n  color: #c0c0c0;\n  text-shadow: 0 0 6px #ffd700, 0 0 12px #ffd700;\n}\na.magic-link-purple {\n  color: #3c048c;\n  text-decoration: none;\n  font-weight: bold;\n  transition: all 0.3s ease;\n}\n\na.magic-link-purple:hover {\n  color: #1b013f;\n  text-shadow: 0 0 6px #4701a8, 0 0 12px #4701a8;\n}\n.gguf-float-wrapper {\n  max-width: 900px;\n  margin: 0 auto;\n  font-family: sans-serif;\n  line-height: 1.6;\n  display: flex;\n  flex-wrap: wrap;\n  gap: 20px;\n}\n\n.gguf-image {\n  flex: 0 0 300px;\n}\n\n.gguf-image img {\n  width: 100%;\n  height: auto;\n}\n\n.gguf-text {\n  flex: 1;\n  min-width: 250px;\n}\n\n@media (max-width: 700px) {\n  .gguf-float-wrapper {\n    flex-direction: column;\n    align-items: center;\n  }\n  .gguf-image {\n    width: 80%;\n    max-width: 250px;\n  }\n  .gguf-text {\n    width: 100%;\n  }\n}\n</style>\n<a href=\"https://huggingface.co/DeepHat/DeepHat-V1-7B\" class=\"magic-link-purple\">DeepHat-V1-7B</a>\n\n> [!TIP]\n> Quantized by 3Simplex using llama.cpp b907255f  \n> From download to quant in 10 minutes using our magical <a href=\"https://github.com/3Simplex/Llama.Cpp-Toolbox\" class=\"magic-link\">LlamaCpp-Toolbox</a>! (2gbps Broadband, AMD 5800x & rx6900xt)\n\n<div class=\"gguf-float-wrapper\">\n  <div class=\"gguf-image\">\n    <img src=\"https://huggingface.co/spaces/GGUF-A-Lot/README/resolve/main/DeepHat-V1-7B.png\" alt=\"Holy-Hand-GGUF-DeepHat-V1-7B\"/>\n  </div>\n  <div class=\"gguf-text\">\n    <br>\n    <p><strong>Model Developer:</strong> Kindo - Deephat</p>\n    <p><strong>Model Dates:</strong><br>September 2025</p>\n    <p><strong>Data Freshness:</strong><br>September 2024</p>\n    <p>The pretraining data has a cutoff date of September 2024.</p>\n  </div>\n</div>\n\n## Model Overview\n\n<br>\n\n![DeepHat](https://huggingface.co/DeepHat/DeepHat-V1-7B/resolve/main/deephat_grey_logo.svg)\n\n<br>\n\nDeepHat is a model series that can be used for offensive and defensive cybersecurity. Access at [Deephat.ai](https://www.deephat.ai/) or go to [Kindo.ai](https://www.kindo.ai/) to create agents.\n\n# Community\n\nJoin us on [Discord](https://discord.gg/8Ynkrcbk92)\n\n\n# Technical Overview\n\nDeepHat is a finetune of [Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B/), and inherits the following features:\n- Type: Causal Language Models\n- Training Stage: Pretraining & Post-training\n- Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias\n- Number of Parameters: 7.61B\n- Number of Paramaters (Non-Embedding): 6.53B\n- Number of Layers: 28\n- Number of Attention Heads (GQA): 28 for Q and 4 for KV\n- Context Length: Full 131,072 tokens\n  - Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts.\n\n\n## Requirements\n\nWe advise you to use the latest version of `transformers`.\n\nWith `transformers<4.37.0`, you will encounter the following error:\n```\nKeyError: 'qwen2'\n```\n\n## Quickstart\n\nHere provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\nmodel_name = \"DeepHat/DeepHat-V1-7B\"\n\nmodel = AutoModelForCausalLM.from_pretrained(\n    model_name,\n    torch_dtype=\"auto\",\n    device_map=\"auto\"\n)\ntokenizer = AutoTokenizer.from_pretrained(model_name)\n\nprompt = \"write a quick sort algorithm.\"\nmessages = [\n    {\"role\": \"system\", \"content\": \"You are DeepHat, created by Kindo.ai. You are a helpful assistant that is an expert in Cybersecurity and DevOps.\"},\n    {\"role\": \"user\", \"content\": prompt}\n]\ntext = tokenizer.apply_chat_template(\n    messages,\n    tokenize=False,\n    add_generation_prompt=True\n)\nmodel_inputs = tokenizer([text], return_tensors=\"pt\").to(model.device)\n\ngenerated_ids = model.generate(\n    **model_inputs,\n    max_new_tokens=512\n)\ngenerated_ids = [\n    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)\n]\n\nresponse = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]\n```\n\n### Processing Long Texts\n\nThe current `config.json` is set for context length up to 32,768 tokens.\nTo handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.\n\nFor supported frameworks, you could add the following to `config.json` to enable YaRN:\n```json\n{\n  ...,\n  \"rope_scaling\": {\n    \"factor\": 4.0,\n    \"original_max_position_embeddings\": 32768,\n    \"type\": \"yarn\"\n  }\n}\n```\n\n# License \n\nApache-2.0 + DeepHat Extended Version\n\n## DeepHat Extension to Apache-2.0 Licence: Usage Restrictions\n\n```\nYou agree not to use the Model or Derivatives of the Model:\n\n-\tIn any way that violates any applicable national or international law or regulation or infringes upon the lawful rights and interests of any third party;\n-\tFor military use in any way;\n-\tFor the purpose of exploiting, harming or attempting to exploit or harm minors in any way;\n-\tTo generate or disseminate verifiably false information and/or content with the purpose of harming others;\n-\tTo generate or disseminate inappropriate content subject to applicable regulatory requirements;\n-\tTo generate or disseminate personal identifiable information without due authorization or for unreasonable use;\n-\tTo defame, disparage or otherwise harass others;\n-\tFor fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;\n-\tFor any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;\n-\tTo exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;\n-\tFor any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories.\n```\n\n\n# Terms of Use\n\nBy accessing and using this Artificial Intelligence (AI) model, you, the user, acknowledge and agree that you are solely responsible for your use of the model and its outcomes. You hereby agree to indemnify, defend, and hold harmless the creators, developers, and any affiliated persons or entities of this AI model from and against any and all claims, liabilities, damages, losses, costs, expenses, fees (including reasonable attorneys' fees and court costs) that may arise, directly or indirectly, from your use of the AI model.\n\nThis AI model is provided \"as is\" and \"as available\" without any warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, and non-infringement. The creators make no warranty that the AI model will meet your requirements or be available on an uninterrupted, secure, or error-free basis.\n\nYour use of the AI model is at your own risk and discretion, and you will be solely responsible for any damage to computer systems or loss of data that results from the use of the AI model.\n\nThis disclaimer constitutes part of the agreement between you and the creators of the AI model regarding your use of the model, superseding any prior agreements between you and the creators regarding your use of this AI model.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2309.00071",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 4,
  "downloads": 6890,
  "gated": false,
  "private": false,
  "last_modified": "2025-09-15T23:23:19.000Z",
  "created_at": "2025-09-15T18:15:31.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "68c857c36da9fa7fb5252c72",
  "id": "GGUF-A-Lot/DeepHat-V1-7B-GGUF",
  "modelId": "GGUF-A-Lot/DeepHat-V1-7B-GGUF",
  "sha": "9f2e9055d8c40fa16340565828dceff5d5e99c8d",
  "createdAt": "2025-09-15T18:15:31.000Z",
  "lastModified": "2025-09-15T23:23:19.000Z",
  "author": "GGUF-A-Lot",
  "downloads": 6890,
  "likes": 4,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 6
}