初始化项目，由ModelHub XC社区提供模型

Model: AROY76/Embedding-gemma-300M-skills Source: Original Platform
2026-05-14 14:04:56 +08:00
commit 1314e53982
17 changed files with 51950 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/1_Pooling/config.json
+++ b/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
+}
--- a/2_Dense/config.json
+++ b/2_Dense/config.json
@@ -0,0 +1,6 @@
+{
+    "in_features": 768,
+    "out_features": 3072,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}
--- a/2_Dense/model.safetensors
+++ b/2_Dense/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1af742f828adba2c01f8449115b07fbf9674a3aff033da7abede06273f06532e
+size 9437272
--- a/3_Dense/config.json
+++ b/3_Dense/config.json
@@ -0,0 +1,6 @@
+{
+    "in_features": 3072,
+    "out_features": 768,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}
--- a/3_Dense/model.safetensors
+++ b/3_Dense/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26afe243655a7f35ef6cb7ffb834ec4cadd22338a10d15ad8347aeed2cb493fb
+size 9437272
--- a/README.md
+++ b/README.md
@@ -0,0 +1,374 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:4992
+- loss:MultipleNegativesRankingLoss
+base_model: google/embeddinggemma-300m
+widget:
+- source_sentence: Client onboarding, implementation, project management, communication,
+    Salesforce, G-suite, Asana, Single Sign-On (SSO), SFTP, data analysis
+  sentences:
+  - A software engineer uses Python and GitHub to automate testing processes.
+  - Setting up clients in Salesforce and G-suite efficiently requires strong project
+    management and clear communication.
+  - Choosing between cloud storage solutions like Dropbox and Google Drive can be
+    challenging.
+- source_sentence: SQL, Excel, stakeholder management, product management
+  sentences:
+  - FastAPI and Flask both enable developers to build robust RESTful APIs efficiently.
+  - Data analysis using SQL and Excel for stakeholder updates in product management.
+  - Project scheduling and Gantt charts for timeline tracking.
+- source_sentence: Power Platform,Robotic Process Automation,Power Automate Cloud
+    & Desktop,Automation Anywhere,PL900,SAP ECC,Generative AI,Power BI
+  sentences:
+  - SAP ECC and PL900 are essential for financial management systems.
+  - Automation Anywhere, Power Platform, and Power Automate Cloud & Desktop are key
+    tools for streamlining business processes.
+  - Guidewire uses a test automation framework to ensure continuous integration and
+    security testing.
+- source_sentence: Critical Care,ICU
+  sentences:
+  - Guiding students through Java programming basics is crucial for their computer
+    engineering education.
+  - Intensive Care, ICU unit
+  - Pediatric Clinic, outpatient
+- source_sentence: successfactors,algorithms,sap,data analysis,natural language processing,software
+    testing,neural networks,development methodologies
+  sentences:
+  - successfactors offers travel packages and vacation deals through its partnership
+    with various hotels.
+  - Azure Data Lake and Cosmos DB are key components of the Microsoft data ecosystem.
+  - successfactors uses advanced algorithms to enhance sap software testing and improve
+    data analysis accuracy.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on google/embeddinggemma-300m
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) on the csv dataset. 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:** [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) <!-- at revision 57c266a740f537b4dc058e1b0cda161fd15afa75 -->
+- **Maximum Sequence Length:** 2048 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - csv
+<!-- - **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': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
+  (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})
+  (2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
+  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
+  (4): Normalize()
+)
+```
+
+## 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("AROY76/Embedding-gemma-300M-skills")
+# Run inference
+queries = [
+    "successfactors,algorithms,sap,data analysis,natural language processing,software testing,neural networks,development methodologies",
+]
+documents = [
+    'successfactors uses advanced algorithms to enhance sap software testing and improve data analysis accuracy.',
+    'successfactors offers travel packages and vacation deals through its partnership with various hotels.',
+    'Azure Data Lake and Cosmos DB are key components of the Microsoft data ecosystem.',
+]
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+# [1, 768] [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+# tensor([[0.7328, 0.0418, 0.0872]])
+```
+
+<!--
+### 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
+
+#### csv
+
+* Dataset: csv
+* Size: 4,992 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                             | positive                                                                         | negative                                                                         |
+  |:--------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                           | string                                                                           |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 32.16 tokens</li><li>max: 121 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 18.5 tokens</li><li>max: 97 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 15.5 tokens</li><li>max: 76 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                        | positive                                                                                                                                                                                                                                                               | negative                                                                                                                                                                                                                                                                   |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Statistical analysis, SQL, Scripting (Ruby, Python, etc.), Version control (git), Web design/UX, Monte Carlo simulations, RoR, Front-end JS, Growth hacking, Airflow, Pandas</code>                                     | <code>Data analysis, databases, programming languages like Ruby or Python, software versioning, user interface design, probability modeling, Ruby on Rails, JavaScript for interfaces, customer growth strategies, workflow automation, data manipulation tools</code> | <code>Cloud storage, hardware configuration, network security, project management methodologies, graphic design software, database normalization techniques, agile development practices, server administration, marketing analytics, containerization technologies</code> |
+  | <code>Graphic Design, digital design, print design, web design, environmental/experiential design, interaction design, brand design, visual design, communication, user research, illustration, digital design systems</code> | <code>Visual design, graphic design, communication, user research, illustration, digital design systems, web design, brand design, interaction design, print design, environmental/experiential design</code>                                                          | <code>Project management, software development, networking, cybersecurity, database administration, IT infrastructure, agile methodologies, cloud computing, hardware engineering, quality assurance</code>                                                                |
+  | <code>problem solving, customer support, writing, grammar</code>                                                                                                                                                              | <code>improving writing skills to enhance clarity and grammar in customer support communications</code>                                                                                                                                                                | <code>designing website layouts for better user experience</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
+
+- `per_device_train_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 2
+- `warmup_ratio`: 0.1
+- `prompts`: task: sentence similarity | query: 
+
+#### 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`: 16
+- `per_device_eval_batch_size`: 8
+- `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`: 2
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `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`: 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}
+- `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
+- `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
+- `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`: False
+- `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`: False
+- `prompts`: task: sentence similarity | query: 
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.2.0
+- Transformers: 4.57.0.dev0
+- PyTorch: 2.9.0+cu126
+- Accelerate: 1.12.0
+- Datasets: 4.0.0
+- Tokenizers: 0.22.1
+
+## 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.*
+-->
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,60 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3TextModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 2048,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 3,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 257,
+  "transformers_version": "4.57.0.dev0",
+  "use_bidirectional_attention": true,
+  "use_cache": true,
+  "vocab_size": 262144
+}
--- a/config_sentence_transformers.json
+++ b/config_sentence_transformers.json
@@ -0,0 +1,26 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.0",
+    "transformers": "4.57.0.dev0",
+    "pytorch": "2.9.0+cu126"
+  },
+  "prompts": {
+    "query": "task: search result | query: ",
+    "document": "title: none | text: ",
+    "BitextMining": "task: search result | query: ",
+    "Clustering": "task: clustering | query: ",
+    "Classification": "task: classification | query: ",
+    "InstructionRetrieval": "task: code retrieval | query: ",
+    "MultilabelClassification": "task: classification | query: ",
+    "PairClassification": "task: sentence similarity | query: ",
+    "Reranking": "task: search result | query: ",
+    "Retrieval": "task: search result | query: ",
+    "Retrieval-query": "task: search result | query: ",
+    "Retrieval-document": "title: none | text: ",
+    "STS": "task: sentence similarity | query: ",
+    "Summarization": "task: summarization | query: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25578498ac8772e51ae06b7b2f4084d242aae15378f446ea301131b420ae77c3
+size 1211486072
--- a/modules.json
+++ b/modules.json
@@ -0,0 +1,32 @@
+[
+  {
+    "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_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 4,
+    "name": "4",
+    "path": "4_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]
--- a/sentence_bert_config.json
+++ b/sentence_bert_config.json
@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 2048,
+    "do_lower_case": false
+}
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216e2a79606fe879c9f17c529c71cd241338407fd5646b595ffd3c4b9ea1d503
+size 33385262
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074
--- a/tokenizer_config.json
+++ b/tokenizer_config.json