Safetensors
Japanese
qwen3_next

hourai2 10m embedding logo

蓬莱2 10m emmbedding

architecture:

  • qwen3next

tarined by:

  • rtx3060 * 1.37h training code in ./training_codes

tokenizer from ku-nlp/gpt2-small-japanese-char

dataset:

  • hotchpotch/sentence_transformer_japanese use llmjp-kaken 30k rows 1 epoch

evals:

{
  "dataset_revision": "5bac629e25799df4c9c80a6a5db983d6cba9e77d",
  "task_name": "JSTS",
  "mteb_version": "2.18.5",
  "scores": {
    "validation": [
      {
        "pearson": 0.411709,
        "spearman": 0.435841,
        "cosine_pearson": 0.411709,
        "cosine_spearman": 0.435841,
        "manhattan_pearson": 0.443867,
        "manhattan_spearman": 0.435179,
        "euclidean_pearson": 0.44478,
        "euclidean_spearman": 0.435818,
        "main_score": 0.435841,
        "hf_subset": "default",
        "languages": [
          "jpn-Jpan"
        ],
        "mteb_version": "2.18.5"
      }
    ]
  },
  "evaluation_time": 26.372312307357788,
  "kg_co2_emissions": null,
  "date": null,
  "evaluation_phases": null
}
{
  "dataset_revision": "5713cd1b76a22b79c3595827c717c72b6cab8852",
  "task_name": "JaQuADRetrieval",
  "mteb_version": "2.18.5",
  "scores": {
    "validation": [
      {
        "ndcg_at_1": 0.01416,
        "ndcg_at_3": 0.01722,
        "ndcg_at_5": 0.02266,
        "ndcg_at_10": 0.03068,
        "ndcg_at_20": 0.04113,
        "ndcg_at_100": 0.07258,
        "ndcg_at_1000": 0.13918,
        "map_at_1": 0.00708,
        "map_at_3": 0.01217,
        "map_at_5": 0.01469,
        "map_at_10": 0.01755,
        "map_at_20": 0.02014,
        "map_at_100": 0.02409,
        "map_at_1000": 0.02622,
        "recall_at_1": 0.00708,
        "recall_at_3": 0.01953,
        "recall_at_5": 0.03027,
        "recall_at_10": 0.05054,
        "recall_at_20": 0.08447,
        "recall_at_100": 0.22681,
        "recall_at_1000": 0.68359,
        "accuracy": 0.00708,
        "precision_at_1": 0.01416,
        "precision_at_3": 0.01302,
        "precision_at_5": 0.01211,
        "precision_at_10": 0.01011,
        "precision_at_20": 0.00845,
        "precision_at_100": 0.00454,
        "precision_at_1000": 0.00137,
        "mrr_at_1": 0.01416,
        "mrr_at_3": 0.024333,
        "mrr_at_5": 0.029142,
        "mrr_at_10": 0.0342,
        "mrr_at_20": 0.038247,
        "mrr_at_100": 0.043459,
        "mrr_at_1000": 0.04537,
        "nauc_ndcg_at_1_max": -0.186884,
        "nauc_ndcg_at_1_std": 0.378631,
        "nauc_ndcg_at_1_diff1": 0.312584,
        "nauc_ndcg_at_3_max": -0.148608,
        "nauc_ndcg_at_3_std": 0.36812,
        "nauc_ndcg_at_3_diff1": 0.17517,
        "nauc_ndcg_at_5_max": -0.122966,
        "nauc_ndcg_at_5_std": 0.336083,
        "nauc_ndcg_at_5_diff1": 0.147033,
        "nauc_ndcg_at_10_max": -0.101487,
        "nauc_ndcg_at_10_std": 0.301252,
        "nauc_ndcg_at_10_diff1": 0.126384,
        "nauc_ndcg_at_20_max": -0.092526,
        "nauc_ndcg_at_20_std": 0.286329,
        "nauc_ndcg_at_20_diff1": 0.11353,
        "nauc_ndcg_at_100_max": -0.072542,
        "nauc_ndcg_at_100_std": 0.287011,
        "nauc_ndcg_at_100_diff1": 0.070295,
        "nauc_ndcg_at_1000_max": -0.092828,
        "nauc_ndcg_at_1000_std": 0.304924,
        "nauc_ndcg_at_1000_diff1": 0.072369,
        "nauc_map_at_1_max": -0.186884,
        "nauc_map_at_1_std": 0.378631,
        "nauc_map_at_1_diff1": 0.312584,
        "nauc_map_at_3_max": -0.155593,
        "nauc_map_at_3_std": 0.369256,
        "nauc_map_at_3_diff1": 0.200387,
        "nauc_map_at_5_max": -0.135306,
        "nauc_map_at_5_std": 0.347719,
        "nauc_map_at_5_diff1": 0.177674,
        "nauc_map_at_10_max": -0.122684,
        "nauc_map_at_10_std": 0.329173,
        "nauc_map_at_10_diff1": 0.159207,
        "nauc_map_at_20_max": -0.117793,
        "nauc_map_at_20_std": 0.323533,
        "nauc_map_at_20_diff1": 0.151419,
        "nauc_map_at_100_max": -0.105846,
        "nauc_map_at_100_std": 0.324242,
        "nauc_map_at_100_diff1": 0.135488,
        "nauc_map_at_1000_max": -0.10753,
        "nauc_map_at_1000_std": 0.326711,
        "nauc_map_at_1000_diff1": 0.135503,
        "nauc_recall_at_1_max": -0.186884,
        "nauc_recall_at_1_std": 0.378631,
        "nauc_recall_at_1_diff1": 0.312584,
        "nauc_recall_at_3_max": -0.135637,
        "nauc_recall_at_3_std": 0.366165,
        "nauc_recall_at_3_diff1": 0.128315,
        "nauc_recall_at_5_max": -0.103997,
        "nauc_recall_at_5_std": 0.322636,
        "nauc_recall_at_5_diff1": 0.104793,
        "nauc_recall_at_10_max": -0.07864,
        "nauc_recall_at_10_std": 0.273391,
        "nauc_recall_at_10_diff1": 0.093104,
        "nauc_recall_at_20_max": -0.069963,
        "nauc_recall_at_20_std": 0.257333,
        "nauc_recall_at_20_diff1": 0.081247,
        "nauc_recall_at_100_max": -0.046774,
        "nauc_recall_at_100_std": 0.258493,
        "nauc_recall_at_100_diff1": 0.019211,
        "nauc_recall_at_1000_max": -0.086654,
        "nauc_recall_at_1000_std": 0.250492,
        "nauc_recall_at_1000_diff1": 0.006271,
        "nauc_precision_at_1_max": -0.186884,
        "nauc_precision_at_1_std": 0.378631,
        "nauc_precision_at_1_diff1": 0.312584,
        "nauc_precision_at_3_max": -0.135637,
        "nauc_precision_at_3_std": 0.366165,
        "nauc_precision_at_3_diff1": 0.128315,
        "nauc_precision_at_5_max": -0.103997,
        "nauc_precision_at_5_std": 0.322636,
        "nauc_precision_at_5_diff1": 0.104793,
        "nauc_precision_at_10_max": -0.07864,
        "nauc_precision_at_10_std": 0.273391,
        "nauc_precision_at_10_diff1": 0.093104,
        "nauc_precision_at_20_max": -0.069963,
        "nauc_precision_at_20_std": 0.257333,
        "nauc_precision_at_20_diff1": 0.081247,
        "nauc_precision_at_100_max": -0.046774,
        "nauc_precision_at_100_std": 0.258493,
        "nauc_precision_at_100_diff1": 0.019211,
        "nauc_precision_at_1000_max": -0.086654,
        "nauc_precision_at_1000_std": 0.250492,
        "nauc_precision_at_1000_diff1": 0.006271,
        "nauc_mrr_at_1_max": -0.186884,
        "nauc_mrr_at_1_std": 0.378631,
        "nauc_mrr_at_1_diff1": 0.312584,
        "nauc_mrr_at_3_max": -0.155593,
        "nauc_mrr_at_3_std": 0.369256,
        "nauc_mrr_at_3_diff1": 0.200387,
        "nauc_mrr_at_5_max": -0.135848,
        "nauc_mrr_at_5_std": 0.342255,
        "nauc_mrr_at_5_diff1": 0.173616,
        "nauc_mrr_at_10_max": -0.119048,
        "nauc_mrr_at_10_std": 0.317863,
        "nauc_mrr_at_10_diff1": 0.15535,
        "nauc_mrr_at_20_max": -0.113849,
        "nauc_mrr_at_20_std": 0.306489,
        "nauc_mrr_at_20_diff1": 0.147553,
        "nauc_mrr_at_100_max": -0.109212,
        "nauc_mrr_at_100_std": 0.304684,
        "nauc_mrr_at_100_diff1": 0.135808,
        "nauc_mrr_at_1000_max": -0.109659,
        "nauc_mrr_at_1000_std": 0.30613,
        "nauc_mrr_at_1000_diff1": 0.137349,
        "hit_rate_at_1": 0.01416,
        "hit_rate_at_3": 0.03906,
        "hit_rate_at_5": 0.06006,
        "hit_rate_at_10": 0.09814,
        "hit_rate_at_20": 0.1582,
        "hit_rate_at_100": 0.38135,
        "hit_rate_at_1000": 0.88721,
        "main_score": 0.03068,
        "hf_subset": "default",
        "languages": [
          "jpn-Jpan"
        ],
        "mteb_version": "2.18.5"
      }
    ]
  },
  "evaluation_time": 42.422733545303345,
  "kg_co2_emissions": null,
  "date": null,
  "evaluation_phases": null
}
Downloads last month
63
Safetensors
Model size
9.73M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for WariHima/hourai2-10m-embedding

Quantizations
1 model

Dataset used to train WariHima/hourai2-10m-embedding

Collection including WariHima/hourai2-10m-embedding