Upload folder using huggingface_hub

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

@@ -0,0 +1,404 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:14131
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: 'Honors Thesis I. Business students with outstanding academic records
+    may undertake an Honors Thesis. The topic is of the student''s choice but must
+    have some original aspect in the question being explored, the data set, or in
+    the methods that are used. It must also be of sufficient academic rigor to meet
+    the approval of a faculty advisor with expertise in the project''s area. Students
+    enroll each semester in a 9-unit independent study course with their faculty advisor
+    for the project (70-500 in the fall and 70-501 in the spring). Students and their
+    faculty advisor develop a course description for the project and submit it for
+    approval as two 9-unit courses to the BA department. Enrollment by permission
+    of the BA Program. Industry: business & management. Level: advanced.'
+  sentences:
+  - project management
+  - statistics
+  - natural language processing
+- source_sentence: 'Psychology of Sleep. TBA Industry: psychology. Level: intermediate.'
+  sentences:
+  - scientific computing
+  - decision making
+  - user research
+- source_sentence: 'Transition Design. Designing for Systems-Level Change. This course
+    will provide an overview of the emerging field of Transition Design, which proposes
+    societal transitions toward more sustainable futures. The idea of intentional
+    (designed) societal transitions has become a global meme and involves an understanding
+    of the complex dynamics of socio-technical-ecological systems which form the context
+    for many of todays wicked problems (climate change, loss of biodiversity, pollution,
+    growing gap between rich/poor, etc.).Through a mix of lecture, readings, classroom
+    activities and projects, students will be introduced to the emerging Transition
+    Design process which focuses on framing problems in large, spatio-temporal contexts,
+    resolving conflict among stakeholder groups and facilitating the co-creation,
+    and transition towards, desirable, long-term futures. This course will prepare
+    students for work in transdisciplinary teams to address large, societal problems
+    that require a deep understanding of the anatomy and dynamics of complex systems.
+    Industry: design & hci. Level: advanced.'
+  sentences:
+  - hardware prototyping
+  - stakeholder management
+  - mathematical modeling
+- source_sentence: 'Advanced Biochemistry. This is a special topics course in which
+    selected topics in biochemistry will be analyzed in depth with emphasis on class
+    discussion of papers from the recent research literature. Topics change yearly.
+    Recent topics have included single molecule analysis of catalysis and conformational
+    changes; intrinsically disordered proteins; cooperative interactions of aspartate
+    transcarbamoylase; and the mechanism of ribosomal protein synthesis. Industry:
+    biological sciences. Level: advanced.'
+  sentences:
+  - control systems
+  - vector calculus
+  - user research
+- source_sentence: 'Metrics for Technology Products & Services. The Metrics for Technology
+    Products & Services course provides an in-depth understanding and practice of
+    applying metrics to plan and track the development of technology products and
+    services and improve them over time by managing their market performance and value
+    delivery. The course utilizes a business lens to understand and leverage metrics
+    to generate questions and provide answers to meet business and customer goals,
+    including delivered value and performance outcomes. Students will be exposed to
+    a set of metrics architectures and their specific applications at different levels
+    of work aggregation, namely team, program, and portfolio. Value stream mapping
+    and analysis will be taught to identify opportunities for delivering value via
+    adoption, cost reductions, and organizational capabilities. Through team-oriented
+    case study assignments, students can select and design metrics systems to address
+    business needs and value generation for product and service development and operations.
+    Industry: business & management. Level: advanced.'
+  sentences:
+  - industrial engineering
+  - presentation skills
+  - product design
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+
+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 c9745ed1d9f207416be6d2e6f8de32d1f16199bf -->
+- **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/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': 256, 'do_lower_case': False, 'architecture': '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)
+
+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 = [
+    'Metrics for Technology Products & Services. The Metrics for Technology Products & Services course provides an in-depth understanding and practice of applying metrics to plan and track the development of technology products and services and improve them over time by managing their market performance and value delivery. The course utilizes a business lens to understand and leverage metrics to generate questions and provide answers to meet business and customer goals, including delivered value and performance outcomes. Students will be exposed to a set of metrics architectures and their specific applications at different levels of work aggregation, namely team, program, and portfolio. Value stream mapping and analysis will be taught to identify opportunities for delivering value via adoption, cost reductions, and organizational capabilities. Through team-oriented case study assignments, students can select and design metrics systems to address business needs and value generation for product and service development and operations. Industry: business & management. Level: advanced.',
+    'product design',
+    'presentation skills',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.3146, 0.2180],
+#         [0.3146, 1.0000, 0.5224],
+#         [0.2180, 0.5224, 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: 14,131 training samples
+* Columns: <code>sentence_0</code> and <code>sentence_1</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                           | sentence_1                                                                      |
+  |:--------|:-------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
+  | type    | string                                                                               | string                                                                          |
+  | details | <ul><li>min: 14 tokens</li><li>mean: 150.13 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 4.14 tokens</li><li>max: 9 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | sentence_1                          |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------|
+  | <code>Design Practicum. This course provides 3 units of pass/fail credit for students participating in a design internship. The student must be registered for this course during the internship, in order to earn the credit. In the summer semester, the course must be paid for as an additional course, as summer courses are not part of the normal fall/spring academic year. At the end of the term, the student's supervisor must email the course coordinator with a brief statement describing the student's activities, and an evaluation of the student's performance. Students are required to submit a statement, reflecting on insights gained from the internship experience. Upon receipt of both statements, the course coordinator will assign a grade of either P or N, depending on the outcome. Industry: design & hci. Level: intermediate.</code> | <code>data analysis</code>          |
+  | <code>Service Design. In this course, we will collectively define and study services and product service systems, and learn the basics of designing them. We will do this through lectures, studio projects, and verbal and written exposition. Classwork will be done individually and in teams. Industry: design & hci. Level: advanced.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | <code>project management</code>     |
+  | <code>Study Abroad. Students are encouraged to pursue various international collaborative programs offered through the department of Electrical and Computer Engineering. Industry: electrical & computer engineering. Level: intro.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | <code>industrial engineering</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`: 64
+- `per_device_eval_batch_size`: 64
+- `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`: 64
+- `per_device_eval_batch_size`: 64
+- `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`: 3
+- `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
+- `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`: 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`: 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`: round_robin
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 2.2624 | 500  | 3.114         |
+
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.1.2
+- Transformers: 4.57.2
+- PyTorch: 2.9.1+cpu
+- Accelerate: 1.12.0
+- Datasets: 4.4.1
+- 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.*
+-->

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.2",
+    "transformers": "4.57.2",
+    "pytorch": "2.9.1+cpu"
+  },
+  "model_type": "SentenceTransformer",
+  "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 sha256:6b1b320682d1ebc33c34228ffcfa97f7a81dc1a230ef9fdd60e52776ff9d55dc
+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"
+  }
+]

sentence_bert_config.json

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

skill_emb_trained.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31178c688f31ee1b689424eb85d700f4763e5e0296d79642a150da7be5615d8c
+size 247424

skills_index.csv

@@ -0,0 +1,162 @@
+row_index,skill_id,skill_name
+0,0,python programming
+1,1,c programming
+2,2,c++ programming
+3,3,java programming
+4,4,matlab programming
+5,5,r programming
+6,6,sql
+7,7,html css javascript
+8,8,web development
+9,9,software engineering
+10,10,object oriented programming
+11,11,functional programming
+12,12,data structures
+13,13,algorithm design
+14,14,operating systems
+15,15,computer architecture
+16,16,distributed systems
+17,17,cloud computing
+18,18,computer networking
+19,19,cybersecurity fundamentals
+20,20,ethical hacking
+21,21,databases
+22,22,data modeling
+23,23,data analysis
+24,24,data visualization
+25,25,data mining
+26,26,machine learning
+27,27,deep learning
+28,28,neural networks
+29,29,reinforcement learning
+30,30,natural language processing
+31,31,computer vision
+32,32,signal processing
+33,33,fourier analysis
+34,34,time series analysis
+35,35,statistics
+36,36,probability theory
+37,37,statistical modeling
+38,38,regression analysis
+39,39,classifiers and clustering
+40,40,optimization methods
+41,41,convex optimization
+42,42,numerical methods
+43,43,numerical linear algebra
+44,44,scientific computing
+45,45,computational thinking
+46,46,mathematical modeling
+47,47,discrete mathematics
+48,48,logic and set theory
+49,49,calculus
+50,50,vector calculus
+51,51,differential equations
+52,52,advanced calculus
+53,53,graph theory
+54,54,network science
+55,55,physics fundamentals
+56,56,classical mechanics
+57,57,electromagnetism
+58,58,thermodynamics
+59,59,fluid mechanics
+60,60,heat transfer
+61,61,materials science
+62,62,chemistry fundamentals
+63,63,mechanical design
+64,64,cad modeling
+65,65,solidworks
+66,66,fusion 360
+67,67,fea analysis
+68,68,cfd analysis
+69,69,mechanical vibrations
+70,70,dynamics
+71,71,kine​matics
+72,72,multibody dynamics
+73,73,robotics fundamentals
+74,74,robot kinematics
+75,75,robot dynamics
+76,76,robot motion planning
+77,77,path planning
+78,78,slam (localization and mapping)
+79,79,robot perception
+80,80,ros (robot operating system)
+81,81,embedded systems
+82,82,microcontrollers
+83,83,embedded linux
+84,84,real-time systems
+85,85,fpgas and digital logic
+86,86,verilog or systemverilog
+87,87,circuit design
+88,88,analog electronics
+89,89,digital electronics
+90,90,pcb design
+91,91,sensor fusion
+92,92,imu processing
+93,93,control systems
+94,94,pid control
+95,95,state-space modeling
+96,96,optimal control (lqr)
+97,97,nonlinear control
+98,98,system identification
+99,99,autonomous systems
+100,100,robot simulation (gazebo mujoco pybullet)
+101,101,hardware prototyping
+102,102,rapid prototyping
+103,103,3d printing
+104,104,manufacturing processes
+105,105,machining and cnc
+106,106,industrial engineering
+107,107,quality engineering
+108,108,reliability engineering
+109,109,failure analysis
+110,110,fmea (failure modes and effects analysis)
+111,111,supply chain fundamentals
+112,112,systems engineering
+113,113,requirements engineering
+114,114,systems integration
+115,115,verification and validation
+116,116,design of experiments
+117,117,human factors engineering
+118,118,human-computer interaction
+119,119,ui ux design
+120,120,user research
+121,121,usability testing
+122,122,technical documentation
+123,123,technical writing
+124,124,research methods
+125,125,scientific experimentation
+126,126,data ethics
+127,127,ai fairness
+128,128,ethics in engineering
+129,129,engineering communication
+130,130,presentation skills
+131,131,communication skills
+132,132,team collaboration
+133,133,leadership
+134,134,project management
+135,135,program management
+136,136,agile development
+137,137,scrum methodology
+138,138,stakeholder management
+139,139,risk management
+140,140,conflict resolution
+141,141,negotiation
+142,142,strategic thinking
+143,143,problem solving
+144,144,critical thinking
+145,145,decision making
+146,146,creativity and innovation
+147,147,adaptability
+148,148,time management
+149,149,mentorship
+150,150,cross-cultural communication
+151,151,entrepreneurship
+152,152,product management
+153,153,product design
+154,154,design thinking
+155,155,information visualization
+156,156,business fundamentals
+157,157,financial literacy
+158,158,economic analysis
+159,159,policy analysis
+160,160,environmental sustainability

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "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_config.json

@@ -0,0 +1,65 @@
+{
+  "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]",
+  "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]"
+}