richarderkhov/ank028_-_llama-3.2-1b-instruct-medmcqa-mgsm8k-sft1-ties-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This is a merge of pre-trained language models created using mergekit.",
    "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\nLlama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties - GGUF\n- Model creator: https://huggingface.co/ank028/\n- Original model: https://huggingface.co/ank028/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q2_K.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q2_K.gguf) | Q2_K | 0.54GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ3_XS.gguf) | IQ3_XS | 0.58GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ3_S.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ3_S.gguf) | IQ3_S | 0.6GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K_S.gguf) | Q3_K_S | 0.6GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ3_M.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ3_M.gguf) | IQ3_M | 0.61GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K.gguf) | Q3_K | 0.64GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K_M.gguf) | Q3_K_M | 0.64GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q3_K_L.gguf) | Q3_K_L | 0.68GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ4_XS.gguf) | IQ4_XS | 0.7GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_0.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_0.gguf) | Q4_0 | 0.72GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.IQ4_NL.gguf) | IQ4_NL | 0.72GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_K_S.gguf) | Q4_K_S | 0.72GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_K.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_K.gguf) | Q4_K | 0.75GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_K_M.gguf) | Q4_K_M | 0.75GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_1.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q4_1.gguf) | Q4_1 | 0.77GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_0.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_0.gguf) | Q5_0 | 0.83GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_K_S.gguf) | Q5_K_S | 0.83GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_K.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_K.gguf) | Q5_K | 0.85GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_K_M.gguf) | Q5_K_M | 0.85GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_1.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q5_1.gguf) | Q5_1 | 0.89GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q6_K.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q6_K.gguf) | Q6_K | 0.95GB |\n| [Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q8_0.gguf](https://huggingface.co/RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf/blob/main/Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties.Q8_0.gguf) | Q8_0 | 1.23GB |\n\n\n\n\nOriginal model description:\n---\nbase_model:\n- ank028/Llama-3.2-1B-Instruct-medmcqa\n- meta-llama/Llama-3.2-1B-Instruct\n- autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1\nlibrary_name: transformers\ntags:\n- mergekit\n- merge\n\n---\n# m_l\n\nThis is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).\n\n## Merge Details\n### Merge Method\n\nThis model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) as a base.\n\n### Models Merged\n\nThe following models were included in the merge:\n* [ank028/Llama-3.2-1B-Instruct-medmcqa](https://huggingface.co/ank028/Llama-3.2-1B-Instruct-medmcqa)\n* [autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1](https://huggingface.co/autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1)\n\n### Configuration\n\nThe following YAML configuration was used to produce this model:\n\n```yaml\nmodels:\n  - model: ank028/Llama-3.2-1B-Instruct-medmcqa\n    parameters:\n      density: 0.5 # density gradient\n      weight: 1.0\n  - model: autoprogrammer/Llama-3.2-1B-Instruct-MGSM8K-sft1\n    parameters:\n      density: 0.5\n      weight: 0.5 # weight gradient\nmerge_method: ties\nbase_model: meta-llama/Llama-3.2-1B-Instruct\nparameters:\n  normalize: true\n  int8_mask: false\ndtype: float16\nname: Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties\n```\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2306.01708",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 185,
  "gated": false,
  "private": false,
  "last_modified": "2025-02-18T17:19:22.000Z",
  "created_at": "2025-02-18T16:56:10.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67b4bbaad9e25b2f4f50e01e",
  "id": "RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf",
  "modelId": "RichardErkhov/ank028_-_Llama-3.2-1B-Instruct-medmcqa-MGSM8K-sft1-ties-gguf",
  "sha": "37f022dba0dc562d5f692da8bad5bf8c15f9db9d",
  "createdAt": "2025-02-18T16:56:10.000Z",
  "lastModified": "2025-02-18T17:19:22.000Z",
  "author": "RichardErkhov",
  "downloads": 185,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}