richarderkhov/wang7776_-_mistral-7b-instruct-v0.2-sparsity-30-v0.1-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model has been pruned to 30% sparsity using the Wanda pruning method. This method requires no retraining or weight updates and still achieves competitive performance. A link to the base model can be found here. # Model Card for Mistral-7B-Instruct-v0.2 The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of Mistral-7B-Instruct-v0.1. For full details of this model please read our paper and release blog post.",
    "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\nMistral-7B-Instruct-v0.2-sparsity-30-v0.1 - GGUF\n- Model creator: https://huggingface.co/wang7776/\n- Original model: https://huggingface.co/wang7776/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q2_K.gguf) | Q2_K | 2.53GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q3_K.gguf) | Q3_K | 3.28GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q4_K.gguf) | Q4_K | 4.07GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q5_K.gguf) | Q5_K | 4.78GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q6_K.gguf) | Q6_K | 5.53GB |\n| [Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf/blob/main/Mistral-7B-Instruct-v0.2-sparsity-30-v0.1.Q8_0.gguf) | Q8_0 | 7.17GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\npipeline_tag: text-generation\ntags:\n- finetuned\ninference: false\n---\n\n# Overview\nThis model has been pruned to 30% sparsity using the [Wanda pruning method](https://arxiv.org/abs/2306.11695). This method requires no retraining or weight updates and still achieves competitive performance. A link to the base model can be found [here](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2).\n\n# Model Card for Mistral-7B-Instruct-v0.2\n\nThe Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an improved instruct fine-tuned version of [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1).\n\nFor full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/la-plateforme/).\n\n## Instruction format\n\nIn order to leverage instruction fine-tuning, your prompt should be surrounded by `[INST]` and `[/INST]` tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.\n\nE.g.\n```\ntext = \"<s>[INST] What is your favourite condiment? [/INST]\"\n\"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> \"\n\"[INST] Do you have mayonnaise recipes? [/INST]\"\n```\n\nThis format is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating) via the `apply_chat_template()` method:\n\n```python\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\ndevice = \"cuda\" # the device to load the model onto\n\nmodel = AutoModelForCausalLM.from_pretrained(\"mistralai/Mistral-7B-Instruct-v0.2\")\ntokenizer = AutoTokenizer.from_pretrained(\"mistralai/Mistral-7B-Instruct-v0.2\")\n\nmessages = [\n    {\"role\": \"user\", \"content\": \"What is your favourite condiment?\"},\n    {\"role\": \"assistant\", \"content\": \"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!\"},\n    {\"role\": \"user\", \"content\": \"Do you have mayonnaise recipes?\"}\n]\n\nencodeds = tokenizer.apply_chat_template(messages, return_tensors=\"pt\")\n\nmodel_inputs = encodeds.to(device)\nmodel.to(device)\n\ngenerated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)\ndecoded = tokenizer.batch_decode(generated_ids)\nprint(decoded[0])\n```\n\n## Model Architecture\nThis instruction model is based on Mistral-7B-v0.1, a transformer model with the following architecture choices:\n- Grouped-Query Attention\n- Sliding-Window Attention\n- Byte-fallback BPE tokenizer\n\n## Troubleshooting\n- If you see the following error:\n```\nTraceback (most recent call last):\nFile \"\", line 1, in\nFile \"/transformers/models/auto/auto_factory.py\", line 482, in from_pretrained\nconfig, kwargs = AutoConfig.from_pretrained(\nFile \"/transformers/models/auto/configuration_auto.py\", line 1022, in from_pretrained\nconfig_class = CONFIG_MAPPING[config_dict[\"model_type\"]]\nFile \"/transformers/models/auto/configuration_auto.py\", line 723, in getitem\nraise KeyError(key)\nKeyError: 'mistral'\n```\n\nInstalling transformers from source should solve the issue\npip install git+https://github.com/huggingface/transformers\n\nThis should not be required after transformers-v4.33.4.\n\n## Limitations\n\nThe Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. \nIt does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to\nmake the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.\n\n## The Mistral AI Team\n\nAlbert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2306.11695",
    "arxiv:2310.06825",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 91,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-25T08:08:13.000Z",
  "created_at": "2024-07-25T05:10:04.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66a1de2c47fcfa880b7dbd56",
  "id": "RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf",
  "modelId": "RichardErkhov/wang7776_-_Mistral-7B-Instruct-v0.2-sparsity-30-v0.1-gguf",
  "sha": "18140f1f133fa1a5c286d2fafc42b7cceaec8b52",
  "createdAt": "2024-07-25T05:10:04.000Z",
  "lastModified": "2024-07-25T08:08:13.000Z",
  "author": "RichardErkhov",
  "downloads": 91,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}