richarderkhov/lightblue_-_reranker_0.5_bincont_filt-gguf overview

{
  "metadata": {},
  "card_data": {
    "pipeline_tag": "text-ranking",
    "frontmatter": {
      "pipeline_tag": "text-ranking"
    },
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the reranker_bincont_filt_train dataset. It achieves the following results on the evaluation set:",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\npipeline_tag: text-ranking\n---\nQuantization 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\nreranker_0.5_bincont_filt - GGUF\n- Model creator: https://huggingface.co/lightblue/\n- Original model: https://huggingface.co/lightblue/reranker_0.5_bincont_filt/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [reranker_0.5_bincont_filt.Q2_K.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q2_K.gguf) | Q2_K | 0.39GB |\n| [reranker_0.5_bincont_filt.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.IQ3_XS.gguf) | IQ3_XS | 0.39GB |\n| [reranker_0.5_bincont_filt.IQ3_S.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.IQ3_S.gguf) | IQ3_S | 0.39GB |\n| [reranker_0.5_bincont_filt.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q3_K_S.gguf) | Q3_K_S | 0.39GB |\n| [reranker_0.5_bincont_filt.IQ3_M.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.IQ3_M.gguf) | IQ3_M | 0.39GB |\n| [reranker_0.5_bincont_filt.Q3_K.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q3_K.gguf) | Q3_K | 0.4GB |\n| [reranker_0.5_bincont_filt.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q3_K_M.gguf) | Q3_K_M | 0.4GB |\n| [reranker_0.5_bincont_filt.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q3_K_L.gguf) | Q3_K_L | 0.42GB |\n| [reranker_0.5_bincont_filt.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.IQ4_XS.gguf) | IQ4_XS | 0.4GB |\n| [reranker_0.5_bincont_filt.Q4_0.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q4_0.gguf) | Q4_0 | 0.4GB |\n| [reranker_0.5_bincont_filt.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.IQ4_NL.gguf) | IQ4_NL | 0.4GB |\n| [reranker_0.5_bincont_filt.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q4_K_S.gguf) | Q4_K_S | 0.45GB |\n| [reranker_0.5_bincont_filt.Q4_K.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q4_K.gguf) | Q4_K | 0.46GB |\n| [reranker_0.5_bincont_filt.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q4_K_M.gguf) | Q4_K_M | 0.46GB |\n| [reranker_0.5_bincont_filt.Q4_1.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q4_1.gguf) | Q4_1 | 0.43GB |\n| [reranker_0.5_bincont_filt.Q5_0.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q5_0.gguf) | Q5_0 | 0.46GB |\n| [reranker_0.5_bincont_filt.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q5_K_S.gguf) | Q5_K_S | 0.48GB |\n| [reranker_0.5_bincont_filt.Q5_K.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q5_K.gguf) | Q5_K | 0.49GB |\n| [reranker_0.5_bincont_filt.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q5_K_M.gguf) | Q5_K_M | 0.49GB |\n| [reranker_0.5_bincont_filt.Q5_1.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q5_1.gguf) | Q5_1 | 0.49GB |\n| [reranker_0.5_bincont_filt.Q6_K.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q6_K.gguf) | Q6_K | 0.61GB |\n| [reranker_0.5_bincont_filt.Q8_0.gguf](https://huggingface.co/RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf/blob/main/reranker_0.5_bincont_filt.Q8_0.gguf) | Q8_0 | 0.63GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: other\nbase_model: Qwen/Qwen2.5-0.5B-Instruct\ntags:\n- llama-factory\n- full\n- generated_from_trainer\nmodel-index:\n- name: reranker_bincont_filt_train\n  results: []\n---\n\n<!-- This model card has been generated automatically according to the information the Trainer had access to. You\nshould probably proofread and complete it, then remove this comment. -->\n\n# reranker_bincont_filt_train\n\nThis model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the reranker_bincont_filt_train dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.1613\n\n## Model description\n\nMore information needed\n\n## Intended uses & limitations\n\nMore information needed\n\n## Training and evaluation data\n\nMore information needed\n\n## Training procedure\n\n### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 1\n- eval_batch_size: 1\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- total_train_batch_size: 8\n- total_eval_batch_size: 8\n- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.01\n- num_epochs: 1.0\n\n### Training results\n\n| Training Loss | Epoch  | Step  | Validation Loss |\n|:-------------:|:------:|:-----:|:---------------:|\n| 0.209         | 0.1000 | 3952  | 0.2207          |\n| 0.1541        | 0.2000 | 7904  | 0.2108          |\n| 0.1519        | 0.3000 | 11856 | 0.2030          |\n| 0.3499        | 0.4000 | 15808 | 0.1939          |\n| 0.1045        | 0.5000 | 19760 | 0.1834          |\n| 0.1887        | 0.6000 | 23712 | 0.1770          |\n| 0.2182        | 0.7001 | 27664 | 0.1695          |\n| 0.1281        | 0.8001 | 31616 | 0.1645          |\n| 0.1463        | 0.9001 | 35568 | 0.1617          |\n\n\n### Framework versions\n\n- Transformers 4.46.1\n- Pytorch 2.4.0+cu121\n- Datasets 3.1.0\n- Tokenizers 0.20.3\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "text-ranking",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 1467,
  "gated": false,
  "private": false,
  "last_modified": "2025-04-02T15:17:54.000Z",
  "created_at": "2025-03-14T03:50:08.000Z",
  "pipeline_tag": "text-ranking",
  "library_name": ""
}

{
  "_id": "67d3a7704d3a41ed9f80f091",
  "id": "RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf",
  "modelId": "RichardErkhov/lightblue_-_reranker_0.5_bincont_filt-gguf",
  "sha": "7c1a37119d9123eaeea066ad03373d82438031ab",
  "createdAt": "2025-03-14T03:50:08.000Z",
  "lastModified": "2025-04-02T15:17:54.000Z",
  "author": "RichardErkhov",
  "downloads": 1467,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-ranking",
  "library_name": "",
  "siblings_count": 24
}