add fine-tuned model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "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

@@ -1,46 +1,442 @@
 ---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- loss:CosineSimilarityLoss
 base_model: sentence-transformers/all-MiniLM-L6-v2
-library_name: transformers.js
-license: apache-2.0
+widget:
+- source_sentence: Oracle Cloud - Infrastructure and Platform Services for Enterprises
+  sentences:
+  - PulseAudio - Ubuntu Wiki
+  - Documentation page not found - Read the Docs
+  - Dwarf Fortress beginner tips - Video Games on Sports Illustrated
+- source_sentence: Suggest opt in User Test - Google Slides
+  sentences:
+  - ReleaseEngineering/TryServer - MozillaWiki
+  - Dwarf Fortress beginner tips - Video Games on Sports Illustrated
+  - Tutanota - Private Mailbox with End-to-End Encryption and Calendar
+- source_sentence: https://portal.naviabenefits.com/part/prioritytasks.aspx
+  sentences:
+  - What to Expect - Pregnancy and Parenting Tips, Week-by-Week Guides
+  - Parents.com - Articles, Recipes, and Ideas for Family Activities
+  - Pinterest - Boards for Collecting and Sharing Inspiration on Any Topic
+- source_sentence: Tidal - High-Fidelity Music Streaming with Master Quality Audio
+  sentences:
+  - Walmart - Everyday Low Prices on Groceries, Electronics, and More
+  - Notion - Integrated Workspace for Notes, Tasks, Databases, and Wikis
+  - Ambient Dreams Playlist on Amazon Music
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    metrics:
+    - type: pearson_cosine
+      value: 0.982180856269761
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.24020738836963906
+      name: Spearman Cosine
 ---
 
-https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 with ONNX weights to be compatible with Transformers.js.
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
 
-## Usage (Transformers.js)
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2). It maps sentences & paragraphs to a 384-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:** [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) <!-- at revision fa97f6e7cb1a59073dff9e6b13e2715cf7475ac9 -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 384 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/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
 
-If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
-```bash
-npm i @huggingface/transformers
 ```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel
+  (1): Pooling({'word_embedding_dimension': 384, '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})
+  (2): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
 
-You can then use the model to compute embeddings like this:
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
 
-```js
-import { pipeline } from '@huggingface/transformers';
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
 
-// Create a feature-extraction pipeline
-const extractor = await pipeline('feature-extraction', 'Xenova/all-MiniLM-L6-v2');
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Tabletop Simulator Hub - Workshop Mods and Board Game Fans',
+    'PC Gamer Club - Official Community for PC Gaming Enthusiasts',
+    'Booking.com - Hotels, Homes, and Vacation Rentals Worldwide',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
 
-// Compute sentence embeddings
-const sentences = ['This is an example sentence', 'Each sentence is converted'];
-const output = await extractor(sentences, { pooling: 'mean', normalize: true });
-console.log(output);
-// Tensor {
-//   dims: [ 2, 384 ],
-//   type: 'float32',
-//   data: Float32Array(768) [ 0.04592696577310562, 0.07328180968761444, ... ],
-//   size: 768
-// }
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
 ```
 
-You can convert this Tensor to a nested JavaScript array using `.tolist()`:
-```js
-console.log(output.tolist());
-// [
-//   [ 0.04592696577310562, 0.07328180968761444, 0.05400655046105385, ... ],
-//   [ 0.08188057690858841, 0.10760223120450974, -0.013241755776107311, ... ]
-// ]
+<!--
+### 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.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.9822     |
+| **spearman_cosine** | **0.2402** |
+
+<!--
+## 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
+* Size: 49,800 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                         | sentence_1                                                                         | label                                                          |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | float                                                          |
+  | details | <ul><li>min: 10 tokens</li><li>mean: 14.76 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 14.64 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.04</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence_0                                                                        | sentence_1                                                                   | label            |
+  |:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:-----------------|
+  | <code>TripAdvisor - Hotel Reviews, Photos, and Travel Forums</code>               | <code>Docker Hub - Container Image Repository for DevOps Environments</code> | <code>0.0</code> |
+  | <code>Mastodon - Decentralized Social Media for Niche Communities</code>          | <code>Allrecipes - User-Submitted Recipes, Reviews, and Cooking Tips</code>  | <code>0.0</code> |
+  | <code>YouTube Music - Music Videos, Official Albums, and Live Performances</code> | <code>ESPN - Sports News, Live Scores, Stats, and Highlights</code>          | <code>0.0</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `num_train_epochs`: 6
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `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`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 6
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `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`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: 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}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `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
+- `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
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step  | Training Loss | spearman_cosine |
+|:------:|:-----:|:-------------:|:---------------:|
+| 0.0754 | 500   | 0.0216        | -               |
+| 0.1509 | 1000  | 0.0178        | -               |
+| 0.2263 | 1500  | 0.016         | -               |
+| 0.3018 | 2000  | 0.015         | -               |
+| 0.3772 | 2500  | 0.0144        | -               |
+| 0.4526 | 3000  | 0.013         | -               |
+| 0.5281 | 3500  | 0.0123        | -               |
+| 0.6035 | 4000  | 0.0119        | -               |
+| 0.6789 | 4500  | 0.0116        | -               |
+| 0.7544 | 5000  | 0.0102        | -               |
+| 0.8298 | 5500  | 0.0092        | -               |
+| 0.9053 | 6000  | 0.0087        | -               |
+| 0.9807 | 6500  | 0.0076        | -               |
+| 1.0561 | 7000  | 0.0068        | -               |
+| 1.1316 | 7500  | 0.0063        | -               |
+| 1.2070 | 8000  | 0.0061        | -               |
+| 1.2824 | 8500  | 0.0059        | -               |
+| 1.3579 | 9000  | 0.0055        | -               |
+| 1.4333 | 9500  | 0.0056        | -               |
+| 1.5088 | 10000 | 0.0045        | -               |
+| 1.5842 | 10500 | 0.004         | -               |
+| 1.6596 | 11000 | 0.0045        | -               |
+| 1.7351 | 11500 | 0.0039        | -               |
+| 1.8105 | 12000 | 0.0044        | -               |
+| 1.8859 | 12500 | 0.0036        | -               |
+| 1.9614 | 13000 | 0.0032        | -               |
+| 2.0368 | 13500 | 0.0034        | -               |
+| 2.1123 | 14000 | 0.0028        | -               |
+| 2.1877 | 14500 | 0.0029        | -               |
+| 2.2631 | 15000 | 0.0031        | -               |
+| 2.3386 | 15500 | 0.0026        | -               |
+| 2.4140 | 16000 | 0.0026        | -               |
+| 2.4894 | 16500 | 0.003         | -               |
+| 2.5649 | 17000 | 0.0027        | -               |
+| 2.6403 | 17500 | 0.0026        | -               |
+| 2.7158 | 18000 | 0.0024        | -               |
+| 2.7912 | 18500 | 0.0025        | -               |
+| 2.8666 | 19000 | 0.002         | -               |
+| 2.9421 | 19500 | 0.0022        | -               |
+| 3.0175 | 20000 | 0.0021        | -               |
+| 3.0929 | 20500 | 0.0021        | -               |
+| 3.1684 | 21000 | 0.0019        | -               |
+| 3.2438 | 21500 | 0.0021        | -               |
+| 3.3193 | 22000 | 0.002         | -               |
+| 3.3947 | 22500 | 0.0018        | -               |
+| 3.4701 | 23000 | 0.0018        | -               |
+| 3.5456 | 23500 | 0.0019        | -               |
+| 3.6210 | 24000 | 0.0017        | -               |
+| 3.6964 | 24500 | 0.0017        | -               |
+| 3.7719 | 25000 | 0.0016        | -               |
+| 3.8473 | 25500 | 0.0016        | -               |
+| 3.9228 | 26000 | 0.0015        | -               |
+| 3.9982 | 26500 | 0.0019        | -               |
+| 4.0736 | 27000 | 0.0016        | -               |
+| 4.1491 | 27500 | 0.0016        | -               |
+| 4.2245 | 28000 | 0.0015        | -               |
+| 4.2999 | 28500 | 0.0015        | -               |
+| 4.3754 | 29000 | 0.0016        | -               |
+| 4.4508 | 29500 | 0.0014        | -               |
+| 4.5263 | 30000 | 0.0015        | -               |
+| 4.6017 | 30500 | 0.0014        | -               |
+| 4.6771 | 31000 | 0.0017        | -               |
+| 4.7526 | 31500 | 0.0014        | -               |
+| 4.8280 | 32000 | 0.0016        | -               |
+| 4.9034 | 32500 | 0.0015        | -               |
+| 4.9789 | 33000 | 0.0014        | -               |
+| 5.0543 | 33500 | 0.0014        | -               |
+| 5.1298 | 34000 | 0.0013        | -               |
+| 5.2052 | 34500 | 0.0014        | -               |
+| 5.2806 | 35000 | 0.0014        | -               |
+| 5.3561 | 35500 | 0.0016        | -               |
+| 5.4315 | 36000 | 0.0013        | -               |
+| 5.5069 | 36500 | 0.0015        | -               |
+| 5.5824 | 37000 | 0.0013        | -               |
+| 5.6578 | 37500 | 0.0016        | -               |
+| 5.7333 | 38000 | 0.0015        | -               |
+| 5.8087 | 38500 | 0.0014        | -               |
+| 5.8841 | 39000 | 0.0015        | -               |
+| 5.9596 | 39500 | 0.0014        | -               |
+| -1     | -1    | -             | 0.2402          |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 3.4.1
+- Transformers: 4.48.2
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## 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",
+}
 ```
 
+<!--
+## 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
 
-Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -1,10 +1,12 @@
 {
-  "_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "/content/model",
   "architectures": [
     "BertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "export_model_type": "transformer",
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -18,7 +20,8 @@
   "num_hidden_layers": 6,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.29.2",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.48.2",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e221ece836c01b12d84ed7f448acaaf5abded8125ff662af4e2d59ae5baf1ab5
+size 90864192

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759c3cd2b7fe7e93933ad23c4c9181b7396442a2ed746ec7c1d46192c469c46e
-size 90387606
+oid sha256:0a2964c169dd7b5c7505025e67622937568a5af7d640cab9f96cfbfbd1da180f
+size 90448255

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40bf4ee16090f5b80c5da880ceb013f821e8dbafd337c1c9f258aa2b7f38e4b4
+size 53958494

onnx/model_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cdb5e58291813b6d6e248ed69010100246821a367fa17b1b81ae9483744533d
-size 45297825
+oid sha256:082fe7356be4fd6e673da6541b76fdb05fd275d236ab6daeb42f933b26b79faa
+size 45317631

onnx/model_int8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdb6f1a0e45b715d0bb9b11772f032c399babd23bfc31fed1c170afc848bdb1
-size 22972370
+oid sha256:35588bbe93db341794f76cb060b240c047daec6fb92783e98ceee67ad55ed2bb
+size 22999753

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3eec3fbe7d0a7319b1d66bfa13b36e66b9a3874e1047d137033c29cbee5414b
+size 54621818

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0b11ca7ec4c063f8b48a87857c5c5cc3d1ccbec85f24e0043469867cdd06f4
+size 30061282

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdb6f1a0e45b715d0bb9b11772f032c399babd23bfc31fed1c170afc848bdb1
-size 22972370
+oid sha256:35588bbe93db341794f76cb060b240c047daec6fb92783e98ceee67ad55ed2bb
+size 22999753

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:607b5f89955c7bbfabf4af4bb302f99fe934bd38c0da0ec02c3680f071d33b71
+size 22999753

quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -2,14 +2,12 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
-    "strategy": {
-      "Fixed": 128
-    },
+    "strategy": "BatchLongest",
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 0,
@@ -30683,4 +30681,4 @@
       "##～": 30521
     }
   }
-}
+}

tokenizer_config.json

@@ -1,15 +1,65 @@
 {
-  "clean_up_tokenization_spaces": true,
+  "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": false,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
   "do_lower_case": true,
+  "extra_special_tokens": {},
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "max_length": 128,
+  "model_max_length": 256,
   "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }