richarderkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This is an untrained base model modified from Mistral-7B-Instruct. It has 1.13 billion parameters.",
    "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\nlmlab-mistral-1b-untrained - GGUF\n- Model creator: https://huggingface.co/lmlab/\n- Original model: https://huggingface.co/lmlab/lmlab-mistral-1b-untrained/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [lmlab-mistral-1b-untrained.Q2_K.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q2_K.gguf) | Q2_K | 0.44GB |\n| [lmlab-mistral-1b-untrained.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.IQ3_XS.gguf) | IQ3_XS | 0.49GB |\n| [lmlab-mistral-1b-untrained.IQ3_S.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.IQ3_S.gguf) | IQ3_S | 0.5GB |\n| [lmlab-mistral-1b-untrained.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q3_K_S.gguf) | Q3_K_S | 0.5GB |\n| [lmlab-mistral-1b-untrained.IQ3_M.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.IQ3_M.gguf) | IQ3_M | 0.51GB |\n| [lmlab-mistral-1b-untrained.Q3_K.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q3_K.gguf) | Q3_K | 0.54GB |\n| [lmlab-mistral-1b-untrained.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q3_K_M.gguf) | Q3_K_M | 0.54GB |\n| [lmlab-mistral-1b-untrained.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q3_K_L.gguf) | Q3_K_L | 0.58GB |\n| [lmlab-mistral-1b-untrained.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.IQ4_XS.gguf) | IQ4_XS | 0.6GB |\n| [lmlab-mistral-1b-untrained.Q4_0.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q4_0.gguf) | Q4_0 | 0.63GB |\n| [lmlab-mistral-1b-untrained.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.IQ4_NL.gguf) | IQ4_NL | 0.63GB |\n| [lmlab-mistral-1b-untrained.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q4_K_S.gguf) | Q4_K_S | 0.63GB |\n| [lmlab-mistral-1b-untrained.Q4_K.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q4_K.gguf) | Q4_K | 0.66GB |\n| [lmlab-mistral-1b-untrained.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q4_K_M.gguf) | Q4_K_M | 0.66GB |\n| [lmlab-mistral-1b-untrained.Q4_1.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q4_1.gguf) | Q4_1 | 0.69GB |\n| [lmlab-mistral-1b-untrained.Q5_0.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q5_0.gguf) | Q5_0 | 0.74GB |\n| [lmlab-mistral-1b-untrained.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q5_K_S.gguf) | Q5_K_S | 0.74GB |\n| [lmlab-mistral-1b-untrained.Q5_K.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q5_K.gguf) | Q5_K | 0.76GB |\n| [lmlab-mistral-1b-untrained.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q5_K_M.gguf) | Q5_K_M | 0.76GB |\n| [lmlab-mistral-1b-untrained.Q5_1.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q5_1.gguf) | Q5_1 | 0.8GB |\n| [lmlab-mistral-1b-untrained.Q6_K.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q6_K.gguf) | Q6_K | 0.87GB |\n| [lmlab-mistral-1b-untrained.Q8_0.gguf](https://huggingface.co/RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf/blob/main/lmlab-mistral-1b-untrained.Q8_0.gguf) | Q8_0 | 1.12GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\nlanguage:\n- en\npipeline_tag: text-generation\n---\n\nSorry everyone this got sort of popular but it doesnt generate understandable text - I think there's a way to make this generate good results w/ relatively little compute I'll experiment a bit later\n\n# LMLab Mistral 1B Untrained\n\nThis is an untrained base model modified from Mistral-7B-Instruct. It has 1.13 billion parameters.\n\n## Untrained\n\nThis model is untrained. **This means it will not generate comprehensible text.**\n\n## Model Details\n\n### Model Description\n\n- **Developed by:** LMLab\n- **License:** Apache 2.0\n- **Parameters:** 1.13 billion (1,134,596,096)\n- **Modified from model:** [`mistralai/Mistral-7B-v0.1`](https://huggingface.co/mistralai/Mistral-7B-v0.1)\n\n### Model Architecture\n\nLMLab Mistral 1B is a transformer model, with the following architecture choices:\n\n* Grouped-Query Attention\n* Sliding-Window Attention\n* Byte-fallback BPE tokenizer\n\n## Usage\n\nUse `MistralForCausalLM`.\n\n```python\nfrom transformers import MistralForCausalLM, AutoTokenizer\ntokenizer = AutoTokenizer.from_pretrained('lmlab/lmlab-mistral-1b-untrained')\nmodel = MistralForCausalLM.from_pretrained('lmlab/lmlab-mistral-1b-untrained')\ntext = \"Once upon a time\"\nencoded_input = tokenizer(text, return_tensors='pt')\noutput = model.generate(**encoded_input)\nprint(tokenizer.decode(output[0]))\n```\n\n## Notice\n\nThis model does not have any moderation systems.\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 93,
  "gated": false,
  "private": false,
  "last_modified": "2024-06-23T10:00:04.000Z",
  "created_at": "2024-06-22T23:43:02.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "667761868edbae20880cfd1b",
  "id": "RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf",
  "modelId": "RichardErkhov/lmlab_-_lmlab-mistral-1b-untrained-gguf",
  "sha": "be42b8b1325617d87749ff9580fa75aeb4cce546",
  "createdAt": "2024-06-22T23:43:02.000Z",
  "lastModified": "2024-06-23T10:00:04.000Z",
  "author": "RichardErkhov",
  "downloads": 93,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}