maziyarpanahi/nous-hermes-2-mixtral-8x7b-sft-wikihow-gguf overview

{
  "metadata": {},
  "card_data": {
    "tags": [
      "quantized",
      "2-bit",
      "3-bit",
      "4-bit",
      "5-bit",
      "6-bit",
      "8-bit",
      "GGUF",
      "transformers",
      "pytorch",
      "tensorboard",
      "safetensors",
      "mixtral",
      "text-generation",
      "axolotl",
      "generated_from_trainer",
      "nous_hermes",
      "wikihow",
      "peft",
      "lora",
      "qlora",
      "adapter",
      "finetune",
      "conversational",
      "dataset:HuggingFaceTB/cosmopedia",
      "base_model:NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
      "license:apache-2.0",
      "autotrain_compatible",
      "endpoints_compatible",
      "text-generation-inference",
      "region:us",
      "text-generation"
    ],
    "model_name": "Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF",
    "base_model": "MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow",
    "inference": false,
    "model_creator": "MaziyarPanahi",
    "pipeline_tag": "text-generation",
    "quantized_by": "MaziyarPanahi",
    "frontmatter": {
      "tags": [
        "quantized",
        "2-bit",
        "3-bit",
        "4-bit",
        "5-bit",
        "6-bit",
        "8-bit",
        "GGUF",
        "transformers",
        "pytorch",
        "tensorboard",
        "safetensors",
        "mixtral",
        "text-generation",
        "axolotl",
        "generated_from_trainer",
        "nous_hermes",
        "wikihow",
        "peft",
        "lora",
        "qlora",
        "adapter",
        "finetune",
        "conversational",
        "dataset:HuggingFaceTB/cosmopedia",
        "base_model:NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
        "license:apache-2.0",
        "autotrain_compatible",
        "endpoints_compatible",
        "text-generation-inference",
        "region:us",
        "text-generation"
      ],
      "model_name": "Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF",
      "base_model": "MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow",
      "inference": "false",
      "model_creator": "MaziyarPanahi",
      "pipeline_tag": "text-generation",
      "quantized_by": "MaziyarPanahi"
    },
    "hero_image_url": "",
    "summary": "pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS=\"-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS\" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS=\"-DLLAMA_CLBLAST=on\" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS=\"-DLLAMA_HIPBLAS=on\" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS=\"-DLLAMA_METAL=on\" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = \"-DLLAMA_OPENBLAS=on\" pip install llama-cpp-python `` #### Simple llama-cpp-python example code `python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path=\"./Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF.Q4_K_M.gguf\",  # Download the model file first n_ctx=32768,  # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( \"system {system_message} user {prompt} assistant\", # Prompt max_tokens=512,  # Generate up to 512 tokens stop=[\"\"],   # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True        # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path=\"./Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF.Q4_K_M.gguf\", chat_format=\"llama-2\")  # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {\"role\": \"system\", \"content\": \"You are a story writing assistant.\"}, { \"role\": \"user\", \"content\": \"Write a story about llamas.\" } ] ) ``",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\ntags:\n- quantized\n- 2-bit\n- 3-bit\n- 4-bit\n- 5-bit\n- 6-bit\n- 8-bit\n- GGUF\n- transformers\n- pytorch\n- tensorboard\n- safetensors\n- mixtral\n- text-generation\n- axolotl\n- generated_from_trainer\n- nous_hermes\n- wikihow\n- peft\n- lora\n- qlora\n- adapter\n- finetune\n- conversational\n- dataset:HuggingFaceTB/cosmopedia\n- base_model:NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT\n- license:apache-2.0\n- autotrain_compatible\n- endpoints_compatible\n- text-generation-inference\n- region:us\n- text-generation\nmodel_name: Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF\nbase_model: MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow\ninference: false\nmodel_creator: MaziyarPanahi\npipeline_tag: text-generation\nquantized_by: MaziyarPanahi\n---\n# [MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF](https://huggingface.co/MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF)\n- Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi)\n- Original model: [MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow](https://huggingface.co/MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow)\n\n## Description\n[MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF](https://huggingface.co/MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF) contains GGUF format model files for [MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow](https://huggingface.co/MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow).\n\n## Examples\n\n```\n<|im_start|> system\nYou are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|> \n<|im_start|> user\nWrite a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|> \n<|im_start|> assistant\n\nOnce upon a time in Universe Seven, there lived two powerful beings - Son Goku, Earth's greatest hero; and Kirby, an interdimensional pink puffball known for his insatiable appetite and ability to copy abilities from those he consumes. One fateful day, these unlikely adversaries would cross paths when they discovered that their once-rivalized worlds were now under threat by none other than...a collaboration between Kirby himself and one of Dragon Ball Z’s most feared villains – Majin Buu!\n\nIt began as any ordinary morning might have started out: breakfast at Capsule Corp., followed by rigorous training exercises led personally by Vegeta (who had since become something like family). However, midway through sparring practice against Cell Jr., Gohan suddenly interrupted them via telepathy—his voice filled with urgency yet tainted slightly with disbelief—\"Dad…Kakarot!\" He hesitated briefly before continuing gravely, \"I just received word from King Kai regarding some disturbingly odd activity happening back home on Popstar.\"\n\nGoku raised an eyebrow curiously but didn't stop practicing until completing his current set. Afterward, wiping sweat off his brow, he asked casually while heading towards Bulma's lab where she was working diligently alongside Trunks & Goten, “So what kind of trouble does my old buddy say we should look into?”\n\nBulma glanced away momentarily from whatever gadgetry held her attention captive long enough to respond dryly without looking up, “Well apparently our favorite little vacuum cleaner seems hellbent on destroying everything again.” She paused dramatically then added sarcastically, “But this time around? Get ready because guess who decided tagging along sounded fun?\" With great flair, she finally revealed the answer written clearly across multiple screens surrounding her workspace, displaying images captured directly from Planet Namek itself showing both Kirby AND MAJIN BUU causing widespread chaos hand-in-hand!!\n\nFor several seconds following confirmation of such preposterous news, silence reigned supreme within the usually bustling confines of Capsule Corporation HQ. Finally breaking free from shock induced paralysis, Goku managed only three words initially, spoken softly almost reverentially, “Buu...and...Kirby?” Then louder, more forcefully demanding clarification, “How could THAT possibly happen?! They don't even exist within same universe let alone work together willingly!”\n\nVegeta scoffed derisively beside him muttering dismissively beneath breath, 'Impossible!' Yet despite initial skepticism evident throughout entire room moments ago, everyone present couldn't deny mounting evidence suggesting otherwise right before eyes...\n\nAnd thus begins epic tale chronicling adventures undertaken joint forces comprised primarily Super Saiyan God Blue empowered protagonist hailing originally from distant planet Vegeta accompanied unexpected albeit reluctant antihero originating entirely separate reality altogether bent solely upon saving existence itself rather than dominion over it unlike certain counterparts sharing similar circumstances elsewhere far removed spatially speaking....<|im_end|>\n```\n\n\n```\n<|im_start|> system\nYou are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|> \n<|im_start|> user\nIf I lay 2 wet shirts out in the sun flat on the ground to dry and it takes 5 hours until they are dry, how long would it take to dry 4 shirts of the same type that way simultanously?<|im_end|> \n<|im_start|> assistant\n\nThe time required for drying multiple shirts simultaneously remains the same as when you dried them one at a time because there is no dependency between the individual drying processes. The factors affecting drying speed include sunlight intensity, air circulation, humidity levels, and fabric properties – none of which change based on whether you're drying two or four shirts concurrently.\nThus, if laying out four wet shirts still permits ample exposure to direct sunlight without overlapping too much (which could hinder efficient evaporation), then those additional garments should also be completely dried within approximately 5 hours under identical environmental conditions.<|im_end|>\n```\n\n\n```\n<|im_start|> system\nYou are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|> \n<|im_start|> user\nexplain step by step 25-4*2+3=?<|im_end|> \n<|im_start|> assistant\n\n\nSure! Let's break down the equation into simpler steps:\n\nGiven expression: 25 - 4 * 2 + 3 = ?\n\nStep 1: Calculate the multiplication inside parentheses (if any). Since there aren't any in this case, move on to Step 2 directly.\n\nStep 2: Perform operations from left to right according to order of precedence – Parentheses > Exponents > Multiplication & Division > Addition & Subtraction. Here we have only addition (+) and subtraction (-), so perform them from left to right.\n\nFirst operation is subtraction: 25 - 8 (since 4 times 2 equals 8), resulting in:\n\n25 - 8 = 17\n\nNext operation is addition; add 3 to our current result:\n\n17 + 3 = 20\n\nSo, the final answer after evaluating all parts of the given expression would be **20**.<|im_end|>\n```\n\n```\n<|im_start|> system\nYou are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|> \n<|im_start|> user\nMark is faster than Mary , Mary is faster than Joe. Is Joe faster than Mark? Let's think step by step<|im_end|> \n<|im_start|> assistant\n\n\nStep 1: Understand the given information\nWe know that Mark is faster than Mary, which we can represent as Mark > Mary (using '>' symbol for comparison). Similarly, Mary is faster than Joe, so we have Mary > Joe.\n\nStep 2: Compare the speeds of Mark and Joe using transitive property\nThe transitive property states that if A > B and B > C, then A > C. Applying this concept here - since we know Mark > Mary and Mary > Joe, we should be able to determine whether Mark > Joe or not.\n\nStep 3: Analyze results\nBy applying the transitive property from Step 2, it becomes evident that because Mark is faster than Mary, who in turn is faster than Joe; therefore logically, yes – Mark would indeed be faster than Joe. So our final statement would look like this - Mark > Joe.<|im_end|>\n```\n\n\n## How to use\nThanks to [TheBloke](https://huggingface.co/TheBloke) for preparing an amazing README on how to use GGUF models:\n\n### About GGUF\n\nGGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.\n\nHere is an incomplete list of clients and libraries that are known to support GGUF:\n\n* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.\n* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.\n* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.\n* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.\n* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.\n* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.\n* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.\n* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.\n* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.\n* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.\n\n### Explanation of quantisation methods\n\n<details>\n  <summary>Click to see details</summary>\n\nThe new methods available are:\n\n* GGML_TYPE_Q2_K - \"type-1\" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)\n* GGML_TYPE_Q3_K - \"type-0\" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.\n* GGML_TYPE_Q4_K - \"type-1\" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.\n* GGML_TYPE_Q5_K - \"type-1\" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw\n* GGML_TYPE_Q6_K - \"type-0\" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw\n\n## How to download GGUF files\n\n**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.\n\nThe following clients/libraries will automatically download models for you, providing a list of available models to choose from:\n\n* LM Studio\n* LoLLMS Web UI\n* Faraday.dev\n\n### In `text-generation-webui`\n\nUnder Download Model, you can enter the model repo: [MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF](https://huggingface.co/MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF) and below it, a specific filename to download, such as: Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF.Q4_K_M.gguf.\n\nThen click Download.\n\n### On the command line, including multiple files at once\n\nI recommend using the `huggingface-hub` Python library:\n\n```shell\npip3 install huggingface-hub\n```\n\nThen you can download any individual model file to the current directory, at high speed, with a command like this:\n\n```shell\nhuggingface-cli download MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False\n```\n</details>\n<details>\n  <summary>More advanced huggingface-cli download usage (click to read)</summary>\n\nYou can also download multiple files at once with a pattern:\n\n```shell\nhuggingface-cli download [MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF](https://huggingface.co/MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF) --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'\n```\n\nFor more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).\n\nTo accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:\n\n```shell\npip3 install hf_transfer\n```\n\nAnd set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:\n\n```shell\nHF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False\n```\n\nWindows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.\n</details>\n\n## Example `llama.cpp` command\n\nMake sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.\n\n```shell\n./main -ngl 35 -m Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p \"<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\"\n```\n\nChange `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.\n\nChange `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.\n\nIf you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`\n\nFor other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)\n\n## How to run in `text-generation-webui`\n\nFurther instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).\n\n## How to run from Python code\n\nYou can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.\n\n### How to load this model in Python code, using llama-cpp-python\n\nFor full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).\n\n#### First install the package\n\nRun one of the following commands, according to your system:\n\n```shell\n# Base ctransformers with no GPU acceleration\npip install llama-cpp-python\n# With NVidia CUDA acceleration\nCMAKE_ARGS=\"-DLLAMA_CUBLAS=on\" pip install llama-cpp-python\n# Or with OpenBLAS acceleration\nCMAKE_ARGS=\"-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS\" pip install llama-cpp-python\n# Or with CLBLast acceleration\nCMAKE_ARGS=\"-DLLAMA_CLBLAST=on\" pip install llama-cpp-python\n# Or with AMD ROCm GPU acceleration (Linux only)\nCMAKE_ARGS=\"-DLLAMA_HIPBLAS=on\" pip install llama-cpp-python\n# Or with Metal GPU acceleration for macOS systems only\nCMAKE_ARGS=\"-DLLAMA_METAL=on\" pip install llama-cpp-python\n\n# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:\n$env:CMAKE_ARGS = \"-DLLAMA_OPENBLAS=on\"\npip install llama-cpp-python\n```\n\n#### Simple llama-cpp-python example code\n\n```python\nfrom llama_cpp import Llama\n\n# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.\nllm = Llama(\n  model_path=\"./Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF.Q4_K_M.gguf\",  # Download the model file first\n  n_ctx=32768,  # The max sequence length to use - note that longer sequence lengths require much more resources\n  n_threads=8,            # The number of CPU threads to use, tailor to your system and the resulting performance\n  n_gpu_layers=35         # The number of layers to offload to GPU, if you have GPU acceleration available\n)\n\n# Simple inference example\noutput = llm(\n  \"<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\", # Prompt\n  max_tokens=512,  # Generate up to 512 tokens\n  stop=[\"</s>\"],   # Example stop token - not necessarily correct for this specific model! Please check before using.\n  echo=True        # Whether to echo the prompt\n)\n\n# Chat Completion API\n\nllm = Llama(model_path=\"./Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF.Q4_K_M.gguf\", chat_format=\"llama-2\")  # Set chat_format according to the model you are using\nllm.create_chat_completion(\n    messages = [\n        {\"role\": \"system\", \"content\": \"You are a story writing assistant.\"},\n        {\n            \"role\": \"user\",\n            \"content\": \"Write a story about llamas.\"\n        }\n    ]\n)\n```\n\n## How to use with LangChain\n\nHere are guides on using llama-cpp-python and ctransformers with LangChain:\n\n* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)\n* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "mistral",
    "quantized",
    "2-bit",
    "3-bit",
    "4-bit",
    "5-bit",
    "6-bit",
    "8-bit",
    "GGUF",
    "pytorch",
    "tensorboard",
    "safetensors",
    "mixtral",
    "text-generation",
    "axolotl",
    "generated_from_trainer",
    "nous_hermes",
    "wikihow",
    "peft",
    "lora",
    "qlora",
    "adapter",
    "finetune",
    "conversational",
    "dataset:HuggingFaceTB/cosmopedia",
    "base_model:NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT",
    "license:apache-2.0",
    "autotrain_compatible",
    "endpoints_compatible",
    "text-generation-inference",
    "region:us",
    "base_model:MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow",
    "base_model:adapter:MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow"
  ],
  "likes": 4,
  "downloads": 718,
  "gated": false,
  "private": false,
  "last_modified": "2024-02-22T10:49:22.000Z",
  "created_at": "2024-02-21T22:33:33.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}

{
  "_id": "65d67a3dbf4c0ccb4731601b",
  "id": "MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF",
  "modelId": "MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF",
  "sha": "4e19783bb6cbfe010b8656e0a14c5943ed20fbc9",
  "createdAt": "2024-02-21T22:33:33.000Z",
  "lastModified": "2024-02-22T10:49:22.000Z",
  "author": "MaziyarPanahi",
  "downloads": 718,
  "likes": 4,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 13
}