Upload folder using huggingface_hub

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": true,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,509 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:35145
+- loss:MultipleNegativesRankingLoss
+base_model: shibing624/text2vec-base-chinese
+widget:
+- source_sentence: 科学史上的重大突破不是均匀分布在时间轴上的。某些短暂时期集中产生了大量突破性发现——比如二十世纪初的物理学革命。之前和之后都是相对平静的渐进期。知识的积累似乎有一个临界点，突破后带来一连串爆发性的进展。
+  sentences:
+  - 超分子凝胶由非共价作用驱动的纤维网络构成，施加剪切力后网络断裂变为溶胶，停止剪切后纤维通过非共价相互作用快速重新组装恢复凝胶态，称为触变性。恢复时间从毫秒到数小时不等，取决于纤维重新成核和生长速率，与可注射生物材料和自修复涂层密切相关。
+  - 政府采购实行公开招标制度：所有供应商密封报价，最低价中标。每个供应商为了中标会尽可能报出接近成本的低价，竞争规则让政府不需要判断合理价格就能以最低成本采购到所需物资。
+  - 国际冲突的爆发呈现出明显的丛集效应：和平年代可能持续几十年，然后短期内多场战争密集爆发。第一次世界大战结束二十年后就爆发了第二次。冲突不是随机均匀分布在历史时间轴上的，而是倾向于成簇出现。
+- source_sentence: Notch受体与相邻细胞（反式）Delta结合时被激活，与本细胞（顺式）Delta结合时则被抑制。这种反式激活-顺式抑制的布尔逻辑确保信号只在不同细胞之间传递。高Delta的细胞因顺式抑制而对Notch信号不敏感，只能作为信号发送者；低Delta的细胞Notch可被激活，只能作为接收者，实现信号流方向的结构性规定，阻止同一细胞既发送又接收产生的自激活回路。
+  sentences:
+  - 单个非线性负载产生的谐波微弱，但大量变频器、整流器同时运行时，各次谐波叠加后总畸变率远超单台设备贡献之和，电能质量严重劣化。
+  - 在线学习算法的遗憾定义为累计损失与最佳固定策略损失之差。乘法权重算法在T轮后遗憾的上界正比于T的平方根乘以动作数对数，随轮数增加人均遗憾趋零。将遗憾最小化算法的均值对应到博弈的策略，所有玩家同时使用此算法时策略均值会收敛到粗糙相关均衡。
+  - 酸奶冷藏期乳酸菌继续缓慢代谢使pH持续下降影响口感与稳定性，菌种选育低后酸化菌株可延长货架期。
+- source_sentence: 一个五十人的班级要选五人组成课题小组。可能的分组方案超过两百万种，其中大部分会因为性格冲突或能力不均而效果不佳。班主任分组时凭直觉筛选的，其实只是这个巨大方案空间中极小的一部分。
+  sentences:
+  - 服务器上的处理器时间和内存总量是固定的，容器技术把总资源切成若干份分配给不同应用——每个应用只能用自己那份不能侵占别人的。资源总量守恒，只是被重新划分和分配。
+  - 二维量子自旋霍尔绝缘体（如HgTe量子阱）边缘存在时间反演保护的螺旋边缘态：自旋向上电子向右传播，自旋向下向左传播。非磁性散射无法打开背散射通道，输运接近量子化。磁性杂质或外加时间反演破缺磁场可打开边缘能隙，使螺旋态失保护。
+  - 电容器组只能以固定容量级别投入或切除，要在有限的投切组合中找到使系统损耗最小的方案。候选方案随组数呈组合增长，需高效搜索策略。
+- source_sentence: 服务业要求工作者管理自身情绪以诱导顾客产生期望感受，这种情感的管理技能被组织系统性地纳入生产过程。长期的情感表演使工作者难以区分真实情感与表演性情感，导致情感麻木、身份混乱或过度认同角色，个体情绪因此不再是私人领域，而是被资本逻辑所规训的劳动力组成部分。
+  sentences:
+  - 萨林斯研究布须曼人后提出'原始丰裕社会'理论：田野计时发现他们每天仅需工作三到四小时即可满足需求，其余时间用于休息社交。需求有限才能被满足，而非资源无限——这是丰裕的另一种实现路径。
+  - 政府设定高于均衡价的价格下限（如最低工资）时，供给超过需求产生过剩。过剩由非价格配给机制分配，如排队、关系或歧视。剩余劳动力与有工作者之间形成租金分割：获得就业者收益增加，失业者损失，总体效率损失取决于过剩规模和配给成本，分配效果高度依赖配给机制本身。
+  - 大雁每年秋天南飞春天北返，路线几乎不变时间高度规律。气温和日照长度的季节性变化触发迁徙本能，迁徙行为年复一年地按固定周期重复，形成了精确的年度循环模式。
+- source_sentence: 当射频波频率精确等于粒子在磁场中的回旋频率时，粒子在连续的半圆轨道上持续被波加速，每圈都获得能量。在共振层附近，能量吸收效率极高，等离子体加热功率呈尖峰状集中。离共振层越远，频率失谐，加热效率急剧下降，体现了共振的选频特性。
+  sentences:
+  - 单位河道长度的水流功率（流量与坡降之积）决定了河床形态：功率低时为沙纹，中等时为沙丘，高时沙丘被冲平形成平坦床面，继续升高则出现逆行沙丘。流量的周期性变化使床面形态在洪枯水期间反复转变，并通过水流阻力影响洪水传播速度。
+  - 北极地区升温速率显著高于全球平均，主因是海冰融化降低反照率、低层大气稳定度高使热量集中近地面，以及水汽与云的正反馈叠加，形成局地温度响应的非线性放大。
+  - 质膜中蛋白质扩散被肌动蛋白皮层形成的纳米尺度围栏分割为约100nm的小区域。蛋白质在区域内自由扩散，偶尔越过围栏跳跃至相邻区域，宏观上呈现比自由扩散慢10倍的限制扩散。这种马尔可夫式跳跃扩散使膜蛋白分布有序化，防止不同信号系统的无限混合，维持膜信号传导的局部性，每次跳跃都是一个独立的随机事件。
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on shibing624/text2vec-base-chinese
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [shibing624/text2vec-base-chinese](https://huggingface.co/shibing624/text2vec-base-chinese). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [shibing624/text2vec-base-chinese](https://huggingface.co/shibing624/text2vec-base-chinese) <!-- at revision 183bb99aa7af74355fb58d16edf8c13ae7c5433e -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False, 'architecture': 'BertModel'})
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    '当射频波频率精确等于粒子在磁场中的回旋频率时，粒子在连续的半圆轨道上持续被波加速，每圈都获得能量。在共振层附近，能量吸收效率极高，等离子体加热功率呈尖峰状集中。离共振层越远，频率失谐，加热效率急剧下降，体现了共振的选频特性。',
+    '单位河道长度的水流功率（流量与坡降之积）决定了河床形态：功率低时为沙纹，中等时为沙丘，高时沙丘被冲平形成平坦床面，继续升高则出现逆行沙丘。流量的周期性变化使床面形态在洪枯水期间反复转变，并通过水流阻力影响洪水传播速度。',
+    '质膜中蛋白质扩散被肌动蛋白皮层形成的纳米尺度围栏分割为约100nm的小区域。蛋白质在区域内自由扩散，偶尔越过围栏跳跃至相邻区域，宏观上呈现比自由扩散慢10倍的限制扩散。这种马尔可夫式跳跃扩散使膜蛋白分布有序化，防止不同信号系统的无限混合，维持膜信号传导的局部性，每次跳跃都是一个独立的随机事件。',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[ 1.0000,  0.7606, -0.3357],
+#         [ 0.7606,  1.0000, -0.3780],
+#         [-0.3357, -0.3780,  1.0000]])
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+* Size: 35,145 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                           | sentence2                                                                           | label                                                         |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                              | float                                                         |
+  | details | <ul><li>min: 43 tokens</li><li>mean: 93.32 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 37 tokens</li><li>mean: 84.51 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 1.0</li><li>mean: 1.0</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                  | sentence2                                                                                                                | label            |
+  |:-----------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>山区溪流的水量变化极其不均匀。枯水期可能几周水量极小甚至断流，一场暴雨后几小时内水量暴涨百倍形成洪峰，之后又快速回落。水量的时间分布高度集中——全年的大部分水量可能集中在几次洪峰中输送。</code> | <code>初次犯罪者被司法系统贴上罪犯标签后因就业歧视和社交排斥回到合法生活困难，惩罚本身提高再犯概率，形成越干预越固化的二级偏差过程。</code>                                             | <code>1.0</code> |
+  | <code>快递公司有十个分拣中心，一个包裹从起点到终点可以走不同路线。如果中转次数不超过三次，可行线路就有几百条。调度系统要从这些方案中选出成本最低的那条，本质上就是在庞大配置空间里做筛选。</code>    | <code>投资同一赛道多家公司计算至少有一家成功的概率，投资数量越多命中概率越高——组合计数式的概率覆盖策略。</code>                                                          | <code>1.0</code> |
+  | <code>冬天把一根铁棒的一端插进火堆，热量从灼热的一端缓缓传向冰冷的另一端。温差越大传热越快，随着两端温度趋近，传热也越来越慢。热量总是自发地从热处流向冷处，直到均匀为止。</code>            | <code>当工资和债券利息条款自动与过去通胀挂钩时，历史通胀被嵌入未来成本，形成强烈的通胀惯性。央行即使提高利率，通胀也需要较长时间才能下降，且会面临更大的产出损失。阿根廷、巴西的历史表明，广泛索引化可将高通胀状态锁定多年。</code> | <code>1.0</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+* Size: 3,905 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                           | sentence2                                                                           | label                                                         |
+  |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                              | float                                                         |
+  | details | <ul><li>min: 44 tokens</li><li>mean: 92.67 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 45 tokens</li><li>mean: 83.57 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 1.0</li><li>mean: 1.0</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence1                                                                                                                                                                                   | sentence2                                                                                                                                   | label            |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>一条爆炸性新闻刚出来时人人讨论，但热度消退的速度惊人——第一天刷屏，第三天就只剩茶余饭后偶尔提起。关注度越低，被提及的频率也越低，新闻像退潮一样逐渐沉寂。</code>                                                                                                  | <code>半导体中双光子吸收（TPA）截面正比于光强平方，低功率时可忽略，高功率超过阈值时吸收急剧增大，导致自幅调制和折射率变化。TPA引起的自由载流子可进一步吸收，形成级联非线性损耗。在非线性光子集成中，TPA是限制硅微腔高Q运转的主要机制，需控制载流子寿命。</code> | <code>1.0</code> |
+  | <code>运动神经末梢释放Agrin蛋白激活MuSK激酶，触发烟碱型乙酰胆碱受体从弥散分布迅速聚集到突触位点下方，密度从100个/μm²升至10000个/μm²以上。聚集体通过Rapsyn锚定后稳定化，突触下肌核上调受体基因转录进一步自我强化聚集。初始聚集后的正反馈放大使受体密度涌现式地跃升至功能阈值以上，是突触形成中局部分子密度涌现为突触功能的典型案例。</code> | <code>单独的应力或腐蚀环境都不足以引发开裂，两者共同作用时裂纹以远超预期的速率扩展。应力腐蚀开裂的危害远大于力学和化学因素的简单叠加，呈超加性涌现。</code>                                                        | <code>1.0</code> |
+  | <code>一段文章中最常用的词出现频率极高，次常用的词频率骤降，罕见词大量但每个都极少出现。有趣的是，无论分析一本书、一个章节还是一段话，这种频率分布的形状都差不多。语言的使用模式在不同文本规模上自我重复。</code>                                                                             | <code>闪电的先导放电从云底向地面延伸时不断分叉，形成树状分枝结构。主通道分出支通道支通道再分出更细的支通道，不同尺度的分叉模式呈现自相似特征。</code>                                                           | <code>1.0</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 5
+- `warmup_ratio`: 0.1
+- `use_mps_device`: True
+- `dataloader_pin_memory`: False
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: None
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: True
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: False
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `hub_revision`: None
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: no
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: True
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step  | Training Loss | Validation Loss |
+|:------:|:-----:|:-------------:|:---------------:|
+| 0.0455 | 100   | 2.7356        | -               |
+| 0.0910 | 200   | 2.5624        | -               |
+| 0.1365 | 300   | 2.4543        | -               |
+| 0.1821 | 400   | 2.3932        | -               |
+| 0.2276 | 500   | 2.2464        | -               |
+| 0.2731 | 600   | 2.0937        | -               |
+| 0.3186 | 700   | 2.1172        | -               |
+| 0.3641 | 800   | 2.0323        | -               |
+| 0.4096 | 900   | 1.9005        | -               |
+| 0.4552 | 1000  | 1.7351        | -               |
+| 0.5007 | 1100  | 1.7081        | -               |
+| 0.5462 | 1200  | 1.5792        | -               |
+| 0.5917 | 1300  | 1.4061        | -               |
+| 0.6372 | 1400  | 1.3286        | -               |
+| 0.6827 | 1500  | 1.1789        | -               |
+| 0.7283 | 1600  | 1.131         | -               |
+| 0.7738 | 1700  | 1.0396        | -               |
+| 0.8193 | 1800  | 1.0363        | -               |
+| 0.8648 | 1900  | 0.9753        | -               |
+| 0.9103 | 2000  | 0.8501        | -               |
+| 0.9558 | 2100  | 0.8085        | -               |
+| 1.0    | 2197  | -             | 0.6340          |
+| 1.0014 | 2200  | 0.7142        | -               |
+| 1.0469 | 2300  | 0.5768        | -               |
+| 1.0924 | 2400  | 0.5857        | -               |
+| 1.1379 | 2500  | 0.5691        | -               |
+| 1.1834 | 2600  | 0.5566        | -               |
+| 1.2289 | 2700  | 0.5359        | -               |
+| 1.2745 | 2800  | 0.5055        | -               |
+| 1.3200 | 2900  | 0.5114        | -               |
+| 1.3655 | 3000  | 0.4625        | -               |
+| 1.4110 | 3100  | 0.4353        | -               |
+| 1.4565 | 3200  | 0.4781        | -               |
+| 1.5020 | 3300  | 0.4141        | -               |
+| 1.5476 | 3400  | 0.4385        | -               |
+| 1.5931 | 3500  | 0.378         | -               |
+| 1.6386 | 3600  | 0.3761        | -               |
+| 1.6841 | 3700  | 0.3788        | -               |
+| 1.7296 | 3800  | 0.3598        | -               |
+| 1.7751 | 3900  | 0.3512        | -               |
+| 1.8207 | 4000  | 0.3588        | -               |
+| 1.8662 | 4100  | 0.3364        | -               |
+| 1.9117 | 4200  | 0.3215        | -               |
+| 1.9572 | 4300  | 0.3074        | -               |
+| 2.0    | 4394  | -             | 0.2764          |
+| 2.0027 | 4400  | 0.3134        | -               |
+| 2.0482 | 4500  | 0.2353        | -               |
+| 2.0938 | 4600  | 0.2632        | -               |
+| 2.1393 | 4700  | 0.2416        | -               |
+| 2.1848 | 4800  | 0.2669        | -               |
+| 2.2303 | 4900  | 0.2456        | -               |
+| 2.2758 | 5000  | 0.2314        | -               |
+| 2.3213 | 5100  | 0.2342        | -               |
+| 2.3669 | 5200  | 0.2518        | -               |
+| 2.4124 | 5300  | 0.2147        | -               |
+| 2.4579 | 5400  | 0.2209        | -               |
+| 2.5034 | 5500  | 0.2377        | -               |
+| 2.5489 | 5600  | 0.2113        | -               |
+| 2.5944 | 5700  | 0.248         | -               |
+| 2.6400 | 5800  | 0.2126        | -               |
+| 2.6855 | 5900  | 0.2253        | -               |
+| 2.7310 | 6000  | 0.2525        | -               |
+| 2.7765 | 6100  | 0.2394        | -               |
+| 2.8220 | 6200  | 0.2254        | -               |
+| 2.8675 | 6300  | 0.1928        | -               |
+| 2.9131 | 6400  | 0.2184        | -               |
+| 2.9586 | 6500  | 0.2255        | -               |
+| 3.0    | 6591  | -             | 0.2227          |
+| 3.0041 | 6600  | 0.1808        | -               |
+| 3.0496 | 6700  | 0.1698        | -               |
+| 3.0951 | 6800  | 0.1765        | -               |
+| 3.1406 | 6900  | 0.1695        | -               |
+| 3.1862 | 7000  | 0.1807        | -               |
+| 3.2317 | 7100  | 0.1721        | -               |
+| 3.2772 | 7200  | 0.184         | -               |
+| 3.3227 | 7300  | 0.2107        | -               |
+| 3.3682 | 7400  | 0.1541        | -               |
+| 3.4137 | 7500  | 0.1708        | -               |
+| 3.4593 | 7600  | 0.1802        | -               |
+| 3.5048 | 7700  | 0.1678        | -               |
+| 3.5503 | 7800  | 0.1646        | -               |
+| 3.5958 | 7900  | 0.1793        | -               |
+| 3.6413 | 8000  | 0.1759        | -               |
+| 3.6868 | 8100  | 0.1568        | -               |
+| 3.7324 | 8200  | 0.1864        | -               |
+| 3.7779 | 8300  | 0.152         | -               |
+| 3.8234 | 8400  | 0.1429        | -               |
+| 3.8689 | 8500  | 0.1765        | -               |
+| 3.9144 | 8600  | 0.1623        | -               |
+| 3.9599 | 8700  | 0.1645        | -               |
+| 4.0    | 8788  | -             | 0.1886          |
+| 4.0055 | 8800  | 0.1499        | -               |
+| 4.0510 | 8900  | 0.1428        | -               |
+| 4.0965 | 9000  | 0.172         | -               |
+| 4.1420 | 9100  | 0.1237        | -               |
+| 4.1875 | 9200  | 0.1418        | -               |
+| 4.2330 | 9300  | 0.1568        | -               |
+| 4.2786 | 9400  | 0.1547        | -               |
+| 4.3241 | 9500  | 0.1514        | -               |
+| 4.3696 | 9600  | 0.1626        | -               |
+| 4.4151 | 9700  | 0.1313        | -               |
+| 4.4606 | 9800  | 0.1673        | -               |
+| 4.5061 | 9900  | 0.1422        | -               |
+| 4.5517 | 10000 | 0.151         | -               |
+| 4.5972 | 10100 | 0.1398        | -               |
+| 4.6427 | 10200 | 0.1286        | -               |
+| 4.6882 | 10300 | 0.1486        | -               |
+| 4.7337 | 10400 | 0.1591        | -               |
+| 4.7792 | 10500 | 0.1503        | -               |
+| 4.8248 | 10600 | 0.1375        | -               |
+| 4.8703 | 10700 | 0.141         | -               |
+| 4.9158 | 10800 | 0.154         | -               |
+| 4.9613 | 10900 | 0.1392        | -               |
+| 5.0    | 10985 | -             | 0.1758          |
+
+</details>
+
+### Framework Versions
+- Python: 3.9.6
+- Sentence Transformers: 5.1.2
+- Transformers: 4.57.6
+- PyTorch: 2.8.0
+- Accelerate: 1.10.1
+- Datasets: 4.5.0
+- Tokenizers: 0.22.2
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.57.6",
+    "pytorch": "2.8.0"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc00f104b5168c391c1f443b82985359eb3f6ed8ad9fc0acf62043beb2270b3
+size 409092920

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 128,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}