maddes8cht/mosaicml-mpt-7b-storywriter-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "tags": [
      "Composer",
      "MosaicML",
      "llm-foundry"
    ],
    "datasets": [
      "the_pile_books3"
    ],
    "inference": false,
    "frontmatter": {
      "license": "apache-2.0",
      "tags": [
        "Composer",
        "MosaicML",
        "llm-foundry"
      ],
      "datasets": [
        "the_pile_books3"
      ],
      "inference": "false"
    },
    "hero_image_url": "https://maddes8cht.github.io/assets/buttons/Huggingface-banner.jpg",
    "summary": "MPT-7b and MPT-30B are part of the family of Mosaic Pretrained Transformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference. --- # Brief MPT-7B Storywriter is a Model based on MPT-7b, designed to read and write fictional stories with super long context lengths. --- # About GGUF format gguf is the current file format used by the ggml library. A growing list of Software is using it and can therefore use this model. The core project making use of the ggml library is the llama.cpp project by Georgi Gerganov # Quantization variants There is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you: # Legacy quants Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are legacy quantization types. Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\ntags:\n- Composer\n- MosaicML\n- llm-foundry\ndatasets:\n- the_pile_books3\ninference: false\n---\n[![banner](https://maddes8cht.github.io/assets/buttons/Huggingface-banner.jpg)]()\n\nI'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information\n\n# mpt-7b-storywriter - GGUF\n- Model creator: [mosaicml](https://huggingface.co/mosaicml)\n- Original model: [mpt-7b-storywriter](https://huggingface.co/mosaicml/mpt-7b-storywriter)\n\nMPT-7b and MPT-30B are part of the family of Mosaic Pretrained Transformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference.\n\n\n---\n# Brief\nMPT-7B Storywriter is a Model based on MPT-7b, designed to read and write fictional stories with super long context lengths.\n\n---\n\n\n\n# About GGUF format\n\n`gguf` is the current file format used by the [`ggml`](https://github.com/ggerganov/ggml) library.\nA growing list of Software is using it and can therefore use this model.\nThe core project making use of the ggml library is the [llama.cpp](https://github.com/ggerganov/llama.cpp) project by Georgi Gerganov\n\n# Quantization variants\n\nThere is a bunch of quantized files available to cater to your specific needs. Here's how to choose the best option for you:\n\n# Legacy quants\n\nQ4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.\nNevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.\n## Note:\nNow there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not *real* K-quants. More details can be found in affected model descriptions.\n(This mainly refers to Falcon 7b and Starcoder models)\n\n# K-quants\n\nK-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load.\nSo, if possible, use K-quants.\nWith a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.\n\n\n\n\n---\n\n# Original Model Card:\n# MPT-7B-StoryWriter-65k+\n\nMPT-7B-StoryWriter-65k+ is a model designed to read and write fictional stories with super long context lengths.\nIt was built by finetuning MPT-7B with a context length of 65k tokens on a filtered fiction subset of the [books3 dataset](https://huggingface.co/datasets/the_pile_books3).\nAt inference time, thanks to [ALiBi](https://arxiv.org/abs/2108.12409), MPT-7B-StoryWriter-65k+ can extrapolate even beyond 65k tokens.\nWe demonstrate generations as long as 84k tokens on a single node of 8 A100-80GB GPUs in our [blogpost](https://www.mosaicml.com/blog/mpt-7b).\n  * License: Apache 2.0\n\nThis model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture.\n\n## Model Date\n\nMay 5, 2023\n\n## Model License\n\nApache 2.0\n\n## Documentation\n\n* [Blog post: Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs](https://www.mosaicml.com/blog/mpt-7b)\n* [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/)\n* Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)!\n\n\n## How to Use\n\nNote: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method. This is because we use a custom model architecture that is not yet part of the `transformers` package.\n\nIt includes options for many training efficiency features such as [FlashAttention (Dao et al. 2022)](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), QK LayerNorm, and more.\n\n```python\nimport transformers\nmodel = transformers.AutoModelForCausalLM.from_pretrained(\n  'mosaicml/mpt-7b-storywriter',\n  trust_remote_code=True\n)\n```\n\nTo use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision:\n```python\nimport torch\nimport transformers\n\nname = 'mosaicml/mpt-7b-storywriter'\n\nconfig = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)\nconfig.attn_config['attn_impl'] = 'triton'\nconfig.init_device = 'cuda:0' # For fast initialization directly on GPU!\n\nmodel = transformers.AutoModelForCausalLM.from_pretrained(\n  name,\n  config=config,\n  torch_dtype=torch.bfloat16, # Load model weights in bfloat16\n  trust_remote_code=True\n)\n```\n\nAlthough the model was trained with a sequence length of 2048 and finetuned with a sequence length of 65536,\nALiBi enables users to increase the maximum sequence length during finetuning and/or inference. For example:\n```python\nimport transformers\n\nname = 'mosaicml/mpt-7b'\n\nconfig = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)\nconfig.max_seq_len = 83968 # (input + output) tokens can now be up to 83968\n\nmodel = transformers.AutoModelForCausalLM.from_pretrained(\n  name,\n  config=config,\n  trust_remote_code=True\n)\n```\n\nThis model was trained with the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer.\n\n```python\nfrom transformers import AutoTokenizer\ntokenizer = AutoTokenizer.from_pretrained(\"EleutherAI/gpt-neox-20b\")\n```\n\nThe model can then be used, for example, within a text-generation pipeline.  \nNote: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html).\n\n```python\nfrom transformers import pipeline\n\npipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0')\n\nwith torch.autocast('cuda', dtype=torch.bfloat16):\n    print(\n        pipe('Here is a recipe for vegan banana bread:\\n',\n            max_new_tokens=100,\n            do_sample=True,\n            use_cache=True))\n```\n\n## Community-Created Resources\n\nThese were not created by MosaicML, but you may find them useful. These links are not an endorsement of the creators or their content.\n\n- [Oobabooga Running MPT-7B-Storywriter](https://youtu.be/QVVb6Md6huA)\n- [NEW MPT-7B-StoryWriter CRUSHES GPT-4!](https://www.youtube.com/watch?v=O9Y_ZdsuKWQ&t=649s) - Has a long section on running locally using Oobabooga\n\n## Example Epilogue\n\nThe full text of the _The Great Gatsby_ (67873 tokens) was fed to the model, followed by the text \"EPILOGUE\"\n\n**TheRealFitzgerald233**:\n\n> ...\n>\n> So we beat on, boats against the current, borne back ceaselessly into the past\n>\n> EPILOGUE\n\n**MPT-7B-StoryWriter**:\n\n>I have lived so long in the shadow of this dream that I may never see the bright sunlight of reality. I may look up some morning and find that I am six feet under, and that Gatsby, who gave me the dream and everything else, will have vanished behind me.\n>\n>And so it was. I had hardly crossed the threshold of the old world when my eye caught the headlines of a newspaper, and I knew at once that my dream was over. I knew that Gatsby was dead.\n>\n>And I knew that day that I didn't love her.\n>\n>That night I took the last train for West Egg, and when I reached home I went directly to my attic and brought down all Gatsby's letters.\n>\n>I have sorted them by date and placed them in the order in which they were written. They are very few in number.\n>\n>They are dated between April of nineteen eighteen and January of nineteen nineteen, and the last one I have here is the one that told me he was dead.\n>\n>There is something in that last letter that frightens me. It is the sense of a finality, of a completeness. I never heard of him after that, and I was glad.\n>\n>But a few months ago I read somewhere that he had been seen in New York. He had become a great man.\n>\n>And I knew that he had not changed at all.\n\n## Model Description\n\nThe architecture is a modification of a standard decoder-only transformer.\n\nThe model has been modified from a standard transformer in the following ways:\n* It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf)\n* It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings\n* It does not use biases\n\n\n| Hyperparameter | Value |\n|----------------|-------|\n|n_parameters | 6.7B |\n|n_layers | 32 |\n| n_heads | 32 |\n| d_model | 4096 |\n| vocab size | 50432 |\n| sequence length | **65536** |\n\n## PreTraining Data\n\nFor more details on the pretraining process, see [MPT-7B](https://huggingface.co/mosaicml/mpt-7b).\n\nThe data was tokenized using the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer.\n\n### Training Configuration\n\nThis model was trained on 8 A100-80GBs for about 2 days using the [MosaicML Platform](https://www.mosaicml.com/platform).\nThe model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the [LION](https://arxiv.org/abs/2302.06675) optimizer.\n\n## Limitations and Biases\n\n_The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_\n\nMPT-7B-StoryWriter can produce factually incorrect output, and should not be relied on to produce factually accurate information.\nMPT-7B-StoryWriter was trained on various public datasets.\nWhile great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.\n\n\n## Acknowledgements\n\nThis model was finetuned by Alex Trott and the MosaicML NLP team\n\n## MosaicML Platform\n\nIf you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-7b).\n\n## Disclaimer\n\nThe license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.\n\n\n## Citation\n\nPlease cite this model using the following format:\n\n```\n@online{MosaicML2023Introducing,\n    author    = {MosaicML NLP Team},\n    title     = {Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs},\n    year      = {2023},\n    url       = {www.mosaicml.com/blog/mpt-7b},\n    note      = {Accessed: 2023-03-28}, % change this date\n    urldate   = {2023-03-28} % change this date\n}\n```\n\n***End of original Model File***\n---\n\n\n## Please consider to support my work\n**Coming Soon:** I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.\n\n<center>\n\n[![GitHub](https://maddes8cht.github.io/assets/buttons/github-io-button.png)](https://maddes8cht.github.io)\n[![Stack Exchange](https://stackexchange.com/users/flair/26485911.png)](https://stackexchange.com/users/26485911)\n[![GitHub](https://maddes8cht.github.io/assets/buttons/github-button.png)](https://github.com/maddes8cht)\n[![HuggingFace](https://maddes8cht.github.io/assets/buttons/huggingface-button.png)](https://huggingface.co/maddes8cht)\n[![Twitter](https://maddes8cht.github.io/assets/buttons/twitter-button.png)](https://twitter.com/maddes1966)\n\n</center>",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "Composer",
    "MosaicML",
    "llm-foundry",
    "dataset:the_pile_books3",
    "arxiv:2108.12409",
    "arxiv:2205.14135",
    "arxiv:2302.06675",
    "license:apache-2.0",
    "region:us"
  ],
  "likes": 3,
  "downloads": 572,
  "gated": false,
  "private": false,
  "last_modified": "2023-11-01T15:36:56.000Z",
  "created_at": "2023-10-17T20:18:26.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "652eec126b9c8f1a45469800",
  "id": "maddes8cht/mosaicml-mpt-7b-storywriter-gguf",
  "modelId": "maddes8cht/mosaicml-mpt-7b-storywriter-gguf",
  "sha": "fd42b842d9c5dc81f49b834189dc6800f398e155",
  "createdAt": "2023-10-17T20:18:26.000Z",
  "lastModified": "2023-11-01T15:36:56.000Z",
  "author": "maddes8cht",
  "downloads": 572,
  "likes": 3,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 16
}