Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 3584,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": true,
+  "include_prompt": true
+}

README.md

@@ -1,3 +1,587 @@
----
-license: apache-2.0
----
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:114699
+- loss:CachedGISTEmbedLoss
+base_model: Alibaba-NLP/gte-Qwen2-7B-instruct
+widget:
+- source_sentence: 'Bus drivers, including those operating in various sectors like
+    public transit, intercity, private, or school services, need strong driving skills,
+    knowledge of traffic laws, and the ability to operate safely in diverse conditions.
+    Additionally, effective communication skills and the ability to handle passenger
+    inquiries and emergencies are crucial.
+
+    [''bus driver'', ''intercity bus driver'', ''private bus operator'', ''transit
+    bus driver'', ''public service vehicle operator'', ''passenger driver'', ''international
+    bus driver'', ''public bus operator'', ''touristic bus driver'', ''coach driver'',
+    ''private coach driver'', ''public bus driver'', ''bus operator'', ''driver of
+    bus'', ''bus driving operator'', ''schoolbus driver'']'
+  sentences:
+  - 'The skill of determining shreds sizes percentage in cigarettes is primarily required
+    by tobacco processing technicians and quality control specialists in the cigarette
+    manufacturing industry, who ensure that the tobacco shreds meet specific size
+    and quality standards for consistent product performance.
+
+    [''determine shreds sizes percentage in cigarettes'', ''determine shreds sizes
+    percentage in cigarettes'', ''determine the shreds sizes percentage of cigarettes'',
+    ''determine shreds size percentages in cigarettes'', ''agree shreds sizes percentage
+    in cigarettes'', ''determine the shreds sizes percentage in cigarettes'', ''confirm
+    shreds sizes percentage in cigarettes'', ''sort shreds sizes percentage in cigarettes'']'
+  - 'Job roles such as curriculum developers, educational consultants, and instructional
+    designers require skills like analyzing, evaluating, and scrutinizing curriculums
+    to improve educational outcomes. For legislative programmes, roles including policy
+    analysts, legislative aides, and compliance officers use skills to test, evaluate,
+    and scrutinize legislative processes to ensure effective and efficient policy
+    implementation.
+
+    [''analyse curriculum'', ''test legislative programmes'', ''evaluate legislative
+    programmes'', ''evaluate curriculum'', ''test curriculum'', ''investigate curriculum'',
+    ''scrutinise curriculum'', ''analyze  curriculum'', ''scrutinise legislative processes'',
+    ''investigate legislative programmes'']'
+  - 'Job roles such as customer service representatives, flight attendants, and hotel
+    concierges require a strong focus on passengers or customers, ensuring their needs
+    and comfort are prioritized to provide excellent service and support.
+
+    [''focus on passengers'', ''prioritise passengers'', ''ensure passenger prioritisation'',
+    ''make passengers a priority'', ''maintain a focus on passengers'', ''ensure passengers
+    are the priority focus'', ''ensure passengers are prioritised'', ''attend to passengers'',
+    ''ensure a focus on passengers'']'
+- source_sentence: 'A medical laboratory assistant, or any of its synonyms such as
+    a biomedical laboratory assistant, requires strong attention to detail, proficiency
+    in using laboratory equipment, and a foundational understanding of medical science.
+    Additionally, skills in sample handling, data recording, and basic research methodologies
+    are crucial for roles like a clinical research assistant or an assistant in medical
+    laboratory.
+
+    [''medical laboratory assistant'', ''medical laboratory research assistant'',
+    ''biomedical laboratory assistant'', ''clinical research assistant'', ''assistant
+    in medical laboratory'', ''biomedical laboratory research assistant'', ''assistant
+    clinical researcher'', ''medical lab assistant'', ''assistant in biomedical laboratory'']'
+  sentences:
+  - 'Job roles such as automotive mechanics, fleet managers, and vehicle technicians
+    require skills to ensure vehicle operability and regular maintenance, which involves
+    diagnosing and repairing issues to keep vehicles roadworthy and operational.
+
+    [''ensure vehicle operability'', ''keep vehicle roadworthy'', ''keep vehicle operational'',
+    ''ensure operability of the vehicle'', ''ensure vehicle remains operational'',
+    ''ensure maintenance of vehicle'', ''ensure regular vehicle maintenance'', ''ensure
+    operation of the vehicle'', ''ensure operability'']'
+  - 'The skill of classroom management is primarily required by teachers and educators
+    at all levels, from kindergarten to higher education, to ensure a productive,
+    safe, and organized learning environment. It involves maintaining discipline,
+    organizing space and materials, and facilitating effective instruction, roles
+    that are crucial for teaching assistants and substitute teachers as well.
+
+    [''perform classroom management'', ''performing classroom management'', ''conduct
+    classroom management'', ''practice classroom management'', ''carry out classroom
+    management'', ''implement classroom management'', ''performs classroom management'']'
+  - 'Job roles requiring expertise in stem cells, including embryonic and adult stem
+    cells, typically include stem cell researchers, regenerative medicine scientists,
+    and biomedical engineers who focus on the development and application of stem
+    cell technologies for therapeutic purposes. Additionally, clinical researchers
+    and medical practitioners in specialized fields such as oncology and hematology
+    may utilize knowledge of stem cells for treatment and research purposes.
+
+    [''stem cells'', ''undifferentiated biological cells'', ''embryonic stem cells'',
+    ''development of stem cells'', ''stem cell'', ''adult stem cells'', ''stem cells'']'
+- source_sentence: 'For roles such as ''physiotherapist'', ''neuromusculoskeletal
+    physiotherapist'', ''osteopath'', and ''chiropractor'', the skills needed include
+    a deep understanding of human anatomy and physiology, strong diagnostic skills,
+    and the ability to apply manual therapy techniques to treat musculoskeletal issues.
+    Additionally, effective communication skills are crucial for explaining treatments
+    and exercises to patients, while adaptability and problem-solving skills are essential
+    for tailoring treatments to individual patient needs.
+
+    [''physiotherapist'', ''neuromusculoskeletal physiotherapist'', ''osteopath'',
+    ''eurythmy therapist'', ''respiratory therapist'', ''remedial physiotherapist'',
+    ''physiotherapist manager'', ''occupational therapist'', ''neurological physiotherapist'',
+    ''occupational physiotherapist'', ''bobath physiotherapist'', ''neuromuscular
+    physiotherapist'', ''manipulative physiotherapist'', ''hydrotherapist'', ''rehabilitation
+    therapist'', ''masseuse'', ''health promotion worker'', ''cardiovascular physiotherapist'',
+    ''respiratory physiotherapist'', ''chiropractor'', ''sports physiotherapist'',
+    ''chiropractic therapist'', ''neurodevelopmental physiotherapist'', ''physical
+    therapist'', ''health and well-being therapist'', ''business physiotherapist'']'
+  sentences:
+  - 'Job roles that require skills in dealing with emergency care situations include
+    emergency medical technicians (EMTs), paramedics, and emergency room nurses or
+    doctors, all of whom must quickly and effectively manage critical health situations
+    to save lives.
+
+    [''deal with emergency care situations'', ''deal with emergency care situation'',
+    ''handle emergency care situation'', ''apply knowledge in emergency care situations'',
+    ''handle emergency care situations'']'
+  - 'Job roles such as fashion designers, stylist coordinators, and jewelry designers
+    require the skill to distinguish and evaluate accessories, their differences,
+    and applications, to ensure the right aesthetic and functional fit for their designs
+    or clients. This skill is crucial for creating cohesive looks and enhancing the
+    overall visual appeal in fashion and design industries.
+
+    [''distinguish accessories'', ''evaluate accessories and their differences'',
+    ''evaluate accessories and their application'', ''differentiate accessories'',
+    ''distinguish accessories and their application'', ''distinguish differences in
+    accessories'']'
+  - 'Job roles that require expertise in curriculum objectives include educational
+    consultants, curriculum developers, and instructional designers, who are tasked
+    with creating and refining educational content and learning goals to meet specific
+    educational standards and student needs. Teachers and headteachers also utilize
+    these skills to align their teaching methods and materials with the set educational
+    targets and aims.
+
+    [''curriculum objectives'', ''curriculum objective'', ''curriculum goals'', ''curriculum
+    targets'', ''curriculum aims'', ''curricula objectives'']'
+- source_sentence: 'A mine surveyor, also known as a mining surveyor or mine planning
+    surveyor, requires expertise in geomatics and mining engineering to accurately
+    map and plan mine operations, ensuring safety and efficiency. They must also possess
+    strong analytical skills and the ability to use specialized software for creating
+    detailed mine plans and maintaining accurate records.
+
+    [''mine surveyor'', ''mining surveyor'', ''mine operations surveyor'', ''mine
+    plan maker'', ''mine records keeper'', ''mine surveyors'', ''planner of mining
+    operations'', ''mine planning surveyor'']'
+  sentences:
+  - 'Job roles such as data analysts, business analysts, and financial analysts require
+    the skill to present reports or prepare statistical reports, as they often need
+    to communicate complex data insights clearly and effectively to stakeholders.
+
+    [''present reports'', ''present a report'', ''submit presentation'', ''prepare
+    statistical reports'']'
+  - 'Job roles such as Food Safety Manager, Quality Assurance Specialist, and Public
+    Health Inspector require the skill of developing food safety programs to ensure
+    compliance with regulations and maintain high standards of food safety in various
+    settings including manufacturing, retail, and public health sectors.
+
+    [''develop food safety programmes'', ''creating food safety programmes'', ''develop
+    programmes for food safety'', ''food safety programmes creating'', ''food safety
+    programmes developing'', ''develop food safety programs'', ''food safety programme
+    developing'', ''food safety programme creating'', ''create food safety programmes'',
+    ''create programmes for food safety'', ''developing food safety programmes'']'
+  - 'The skill of using a sander, whether it be a handheld, manual, automatic, or
+    drywall sander, is primarily required by construction workers, carpenters, and
+    drywall installers for tasks such as roughening and smoothing wall surfaces to
+    prepare them for painting or finishing.
+
+    [''use sander'', ''use handheld sander'', ''roughening of wall surfaces'', ''use
+    drywall sander'', ''sanding of wall surfaces'', ''using sander'', ''sander usage'',
+    ''use manual sander'', ''drywall sanding'', ''use automatic sander'']'
+- source_sentence: 'An insulation supervisor, regardless of the specific type of insulation
+    material or installation area, requires strong project management skills, knowledge
+    of building codes and safety regulations, and expertise in insulation techniques
+    to oversee the installation process effectively and ensure quality standards are
+    met.
+
+    [''insulation supervisor'', ''supervisor of installation of insulating materials'',
+    ''supervisor of insulation materials installation'', ''supervisor of installation
+    of insulation'', ''solid wall insulation installation supervisor'', ''insulation
+    installers supervisor'', ''cavity wall insulation installation supervisor'', ''loft
+    insulation installation supervisor'']'
+  sentences:
+  - 'Job roles such as Food Safety Inspector, Public Health Officer, and Environmental
+    Health Specialist require the skill of taking action on food safety violations
+    to ensure compliance with health regulations and maintain public safety standards.
+
+    [''take action on food safety violations'', ''invoke action on food safety violations'',
+    ''agree action on food safety violations'', ''pursue action on food safety violations'',
+    ''determine action on food safety violations'']'
+  - 'Job roles that require skills in operating and supervising textile printing machines
+    include Textile Printer Operators, Printing Machine Technicians, and Textile Production
+    Specialists. These roles involve setting up, running, and maintaining printing
+    machinery to ensure high-quality textile printing.
+
+    [''tend textile printing machines'', ''activate and supervise printing machines
+    for textile material'', ''activate and supervise textile printing machines'',
+    ''tend printing machines for textile'', ''tend printing machines for textile material'',
+    ''care for textile printing machines'', ''operate printing machines for textile
+    material'', ''operate textile printing machines'']'
+  - 'The skill of installing insulation material is primarily required by job roles
+    such as insulation workers, HVAC technicians, and construction specialists, who
+    are responsible for improving energy efficiency and thermal comfort in buildings
+    by correctly fitting and fixing insulation materials in various structures.
+
+    [''install insulation material'', ''insulate structure'', ''fix insulation'',
+    ''insulation material installation'', ''installation of insulation material'',
+    ''fitting insulation'', ''insulating structure'', ''installing insulation material'',
+    ''fixing insulation'', ''fit insulation'']'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# Job-Skill matching fintuned Alibaba-NLP/gte-Qwen2-7B-instruct lora
+
+Top performing model on [TalentCLEF 2025](https://talentclef.github.io/talentclef/) Task B.  Use it for job title <-> skill set matching
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [Alibaba-NLP/gte-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct) <!-- at revision a8d08b36ada9cacfe34c4d6f80957772a025daf2 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 3584 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
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: Qwen2Model 
+  (1): Pooling({'word_embedding_dimension': 3584, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, '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("pj-mathematician/JobSkillGTE-7b-lora")
+# Run inference
+sentences = [
+    "An insulation supervisor, regardless of the specific type of insulation material or installation area, requires strong project management skills, knowledge of building codes and safety regulations, and expertise in insulation techniques to oversee the installation process effectively and ensure quality standards are met.\n['insulation supervisor', 'supervisor of installation of insulating materials', 'supervisor of insulation materials installation', 'supervisor of installation of insulation', 'solid wall insulation installation supervisor', 'insulation installers supervisor', 'cavity wall insulation installation supervisor', 'loft insulation installation supervisor']",
+    "The skill of installing insulation material is primarily required by job roles such as insulation workers, HVAC technicians, and construction specialists, who are responsible for improving energy efficiency and thermal comfort in buildings by correctly fitting and fixing insulation materials in various structures.\n['install insulation material', 'insulate structure', 'fix insulation', 'insulation material installation', 'installation of insulation material', 'fitting insulation', 'insulating structure', 'installing insulation material', 'fixing insulation', 'fit insulation']",
+    "Job roles such as Food Safety Inspector, Public Health Officer, and Environmental Health Specialist require the skill of taking action on food safety violations to ensure compliance with health regulations and maintain public safety standards.\n['take action on food safety violations', 'invoke action on food safety violations', 'agree action on food safety violations', 'pursue action on food safety violations', 'determine action on food safety violations']",
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 3584]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### 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: 114,699 training samples
+* Columns: <code>anchor</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                               | positive                                                                             |
+  |:--------|:-------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                               | string                                                                               |
+  | details | <ul><li>min: 73 tokens</li><li>mean: 133.53 tokens</li><li>max: 333 tokens</li></ul> | <ul><li>min: 44 tokens</li><li>mean: 104.56 tokens</li><li>max: 236 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
+  |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>A technical director or any of its synonyms requires a strong blend of technical expertise and leadership skills, including the ability to oversee technical operations, manage teams, and ensure the successful execution of technical projects while maintaining operational efficiency and innovation.<br>['technical director', 'technical and operations director', 'head of technical', 'director of technical arts', 'head of technical department', 'technical supervisor', 'technical manager']</code> | <code>Job roles that require promoting health and safety include occupational health and safety specialists, safety managers, and public health educators, all of whom work to ensure safe and healthy environments in workplaces and communities.<br>['promote health and safety', 'promote importance of health and safety', 'promoting health and safety', 'advertise health and safety']</code>                                                                                                                                                                                                          |
+  | <code>A technical director or any of its synonyms requires a strong blend of technical expertise and leadership skills, including the ability to oversee technical operations, manage teams, and ensure the successful execution of technical projects while maintaining operational efficiency and innovation.<br>['technical director', 'technical and operations director', 'head of technical', 'director of technical arts', 'head of technical department', 'technical supervisor', 'technical manager']</code> | <code>Job roles that require organizing rehearsals include directors, choreographers, and conductors in theater, dance, and music ensembles, who must efficiently plan and schedule practice sessions to prepare performers for a successful final performance.<br>['organise rehearsals', 'organise rehearsal', 'organize rehearsals', 'plan rehearsals', 'arrange rehearsals', 'organising rehearsals', 'schedule rehearsals']</code>                                                                                                                                                                      |
+  | <code>A technical director or any of its synonyms requires a strong blend of technical expertise and leadership skills, including the ability to oversee technical operations, manage teams, and ensure the successful execution of technical projects while maintaining operational efficiency and innovation.<br>['technical director', 'technical and operations director', 'head of technical', 'director of technical arts', 'head of technical department', 'technical supervisor', 'technical manager']</code> | <code>Job roles such as Health and Safety Managers, Environmental Health Officers, and Risk Management Specialists often require the skill of negotiating health and safety issues with third parties to ensure compliance and protection standards are met across different organizations and sites.<br>['negotiate health and safety issues with third parties', 'agree with third parties on health and safety', 'negotiate issues on health and safety with third parties', 'negotiate with third parties on health and safety issues', 'negotiate health and safety matters with third parties']</code> |
+* Loss: [<code>CachedGISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedgistembedloss) with these parameters:
+  ```json
+  {'guide': SentenceTransformer(
+    (0): Transformer({'max_seq_length': 128, '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()
+  ), 'temperature': 0.01, 'mini_batch_size': 48, 'margin_strategy': 'absolute', 'margin': 0.0}
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 128
+- `per_device_eval_batch_size`: 128
+- `gradient_accumulation_steps`: 2
+- `num_train_epochs`: 2
+- `warmup_ratio`: 0.05
+- `log_on_each_node`: False
+- `fp16`: True
+- `dataloader_num_workers`: 4
+- `fsdp`: ['full_shard', 'auto_wrap']
+- `fsdp_config`: {'transformer_layer_cls_to_wrap': ['Qwen2DecoderLayer'], 'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `ddp_find_unused_parameters`: True
+- `gradient_checkpointing`: True
+- `batch_sampler`: no_duplicates
+
+#### 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`: 128
+- `per_device_eval_batch_size`: 128
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `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`: 1.0
+- `num_train_epochs`: 2
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.05
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: False
+- `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`: True
+- `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`: True
+- `dataloader_num_workers`: 4
+- `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`: ['full_shard', 'auto_wrap']
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'transformer_layer_cls_to_wrap': ['Qwen2DecoderLayer'], 'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `tp_size`: 0
+- `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`: True
+- `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`: True
+- `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
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.0156 | 1    | 21.5186       |
+| 0.0312 | 2    | 21.4075       |
+| 0.0469 | 3    | 21.0309       |
+| 0.0625 | 4    | 20.7294       |
+| 0.0781 | 5    | 20.9851       |
+| 0.0938 | 6    | 21.3215       |
+| 0.1094 | 7    | 19.8458       |
+| 0.125  | 8    | 18.52         |
+| 0.1406 | 9    | 17.622        |
+| 0.1562 | 10   | 17.5794       |
+| 0.1719 | 11   | 15.8784       |
+| 0.1875 | 12   | 14.5842       |
+| 0.2031 | 13   | 13.3324       |
+| 0.2188 | 14   | 12.3194       |
+| 0.2344 | 15   | 11.2523       |
+| 0.25   | 16   | 10.7172       |
+| 0.2656 | 17   | 10.0063       |
+| 0.2812 | 18   | 9.5643        |
+| 0.2969 | 19   | 9.2463        |
+| 0.3125 | 20   | 8.6533        |
+| 0.3281 | 21   | 8.0588        |
+| 0.3438 | 22   | 8.1866        |
+| 0.3594 | 23   | 7.6767        |
+| 0.375  | 24   | 6.9832        |
+| 0.3906 | 25   | 6.7932        |
+| 0.4062 | 26   | 6.292         |
+| 0.4219 | 27   | 6.1263        |
+| 0.4375 | 28   | 5.8976        |
+| 0.4531 | 29   | 5.7214        |
+| 0.4688 | 30   | 5.6451        |
+| 0.4844 | 31   | 5.6232        |
+| 0.5    | 32   | 5.2984        |
+| 0.5156 | 33   | 5.0322        |
+| 0.5312 | 34   | 4.9435        |
+| 0.5469 | 35   | 4.737         |
+| 0.5625 | 36   | 4.4266        |
+| 0.5781 | 37   | 4.5082        |
+| 0.5938 | 38   | 4.315         |
+| 0.6094 | 39   | 4.269         |
+| 0.625  | 40   | 4.2473        |
+| 0.6406 | 41   | 4.2054        |
+| 0.6562 | 42   | 4.2172        |
+| 0.6719 | 43   | 3.8311        |
+| 0.6875 | 44   | 4.0803        |
+| 0.7031 | 45   | 4.2809        |
+| 0.7188 | 46   | 4.1843        |
+| 0.7344 | 47   | 3.9913        |
+| 0.75   | 48   | 3.9465        |
+| 0.7656 | 49   | 4.0828        |
+| 0.7812 | 50   | 4.0018        |
+| 0.7969 | 51   | 3.8023        |
+| 0.8125 | 52   | 3.897         |
+| 0.8281 | 53   | 3.8941        |
+| 0.8438 | 54   | 3.7708        |
+| 0.8594 | 55   | 3.8051        |
+| 0.875  | 56   | 3.7117        |
+| 0.8906 | 57   | 3.8584        |
+| 0.9062 | 58   | 3.6421        |
+| 0.9219 | 59   | 3.7097        |
+| 0.9375 | 60   | 3.6906        |
+| 0.9531 | 61   | 3.7011        |
+| 0.9688 | 62   | 3.744         |
+| 0.9844 | 63   | 3.6493        |
+| 1.0    | 64   | 3.5659        |
+
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 4.1.0
+- Transformers: 4.51.2
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+<!--
+## 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.*
+-->

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Alibaba-NLP/gte-Qwen2-7B-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "FEATURE_EXTRACTION",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b19997222abf3f401feb7d5002ee7c4fca3628033ec0bfad3614802cfe6aad2
+size 80769088

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config_sentence_transformers.json

@@ -0,0 +1,12 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.51.2",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {
+    "query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

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"
+  }
+]

pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea930d6861c49583cf276ed733f39e2fa8324785d9a75e05c071a19021f06b0
+size 28357611916

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 512,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f79052deba517b0663d877714e117a31a4a6243cddb85fc4443c80a2fa65a20
+size 11419302

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "Alibaba-NLP/gte-Qwen2-7B-instruct--tokenization_qwen.Qwen2Tokenizer",
+      "Alibaba-NLP/gte-Qwen2-7B-instruct--tokenization_qwen.Qwen2TokenizerFast"
+    ]
+  },
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3eefa9df18ebb7dd5e0b78d0a8fb7ce7158d7619b014c77871fdafb78ac544
+size 5688