Initial commit: Fine-tuned embedding-gemma-300m on GeoGPT-QA dataset

.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": 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/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 768,
+    "out_features": 3072,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1480daa0ed50c918de639c0a1cdcd27fe04f6e8d5ff77120f1eb956b0f92166a
+size 9437272

3_Dense/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 3072,
+    "out_features": 768,
+    "bias": false,
+    "activation_function": "torch.nn.modules.linear.Identity"
+}

3_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d32c1e2af81ea991978bf5dc7c92c7731f4ada3efe2c09f02ac73ca0d51b0a3
+size 9437272

README.md

@@ -0,0 +1,488 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:41432
+- loss:MultipleNegativesRankingLoss
+base_model: google/embeddinggemma-300m
+widget:
+- source_sentence: How does precipitation influence the water use efficiency and carbon
+    isotopes of Picea meyeri, and what are the implications for climate change studies?
+  sentences:
+  - In the study of starry flounders (Platichthys stellatus), cortisol levels increased
+    with increasing water temperature and then gradually decreased. This suggests
+    that cortisol, a stress hormone, is elevated as a response to higher water temperatures,
+    indicating that the fish experience stress under these conditions. The increase
+    in cortisol levels is part of the fish's physiological response to environmental
+    stressors, such as temperature changes, which can affect their survival and overall
+    health.
+  - The FY-4A/AGRI LST products effectively capture surface temperatures in Hunan
+    Province, with a correlation coefficient (R) of 0.893. However, they exhibit a
+    relatively high error level, with a bias of ?6.295 °C and a root mean square error
+    (RMSE) of 8.58 °C, particularly in capturing high LST values. The performance
+    of this product is superior in the eastern flat terrain area of Hunan Province
+    compared to the western mountainous region. Environmental conditions in the mountainous
+    areas cause systematic errors that contribute to instability in detection deviation.
+    Surface heat resources are more abundant in eastern Hunan Province than in the
+    mountainous areas located to the west and south, and their detailed distribution
+    at finer scales is mainly influenced by terrain and climate conditions. There
+    is no obvious seasonal difference in the distribution of heat resources except
+    in winter, and rapid urbanization within the Chang–Zhu–Tan urban agglomeration
+    over two years has significantly altered the spatial distribution pattern of surface
+    heat resources across Hunan Province.
+  - The water use efficiency (WUE) of Picea meyeri is significantly influenced by
+    precipitation, along with temperature. The study found that there is a significant
+    positive correlation between the WUE sequence and temperature. However, due to
+    the combined effects of precipitation and temperature, Picea meyeri is subject
+    to drought stress to some extent. This indicates that while temperature is the
+    main climatic factor affecting the δ13C and WUE of Picea meyeri, precipitation
+    also plays a crucial role in the plant's response to climate change. These findings
+    are important for understanding the impacts of climate change on tree species
+    and their ability to adapt to changing environmental conditions.
+- source_sentence: How does the warming of the Southern Indian Ocean (SIO) compare
+    to its impact on cyclone destruction potential in the recent period versus the
+    earlier period?
+  sentences:
+  - Green roofing systems are adopted as part of Nature-Based Solutions (NBS) to control
+    urban stormwater runoff and mitigate urban flood risks. Unlike traditional roofing
+    methods, green roofs help manage stormwater by absorbing and retaining rainfall,
+    reducing the volume and rate of runoff. However, there is currently no specific
+    widely recognized standard or code dedicated to determining the hydrological performance
+    of green roofs as a whole system, and no test protocols to regulate their design.
+    This highlights the need for a standardized test method to evaluate the hydrological
+    performance of green roofing systems, making them a more reliable solution for
+    flood resilience in cities affected by climate change.
+  - 'In the monitoring project conducted in Chengdu, Shuangliu (SL) was one of the
+    three urban sites studied. The key findings regarding the sources and contributions
+    of VOCs to ozone formation in Shuangliu included the identification of five dominant
+    VOC sources: vehicular exhaust and fuel evaporation, solvent utilization, biogenic
+    background, secondary formation, and industrial emissions. Before the control
+    measures were implemented, vehicular exhaust and fuel evaporation were the highest
+    contributors. During the control period, the contribution from vehicular exhaust
+    was reduced the most at Shuangliu. VOC species such as xylenes, toluene, and propene,
+    which are primarily from vehicular and industrial emissions and solvent utilization,
+    were found to be the dominant precursors for ozone formation potential (OFP).
+    These results suggest that effective control of photochemical pollutants, particularly
+    from vehicular and industrial sources, is crucial for reducing ozone formation
+    in Chengdu.'
+  - The warming of the Southern Indian Ocean (SIO) has led to a doubling of the Power
+    Dissipation Index (PDI) during 1999–2016 compared to 1980–1998. This increase
+    is primarily due to an increase in the intensity and duration of cyclones, associated
+    with higher sea surface temperatures and upper ocean heat content.
+- source_sentence: How do the findings of the study on Azotobacter paspali bacteria
+    in Iraq relate to the impact of nitrogen on air pollution, and what implications
+    does this have for future research and applications in both environmental and
+    agricultural contexts?
+  sentences:
+  - Quartz is one of the minerals present in the limonite ore sample from the Wolo
+    mine area. The ore sample contains various minerals including chlorite, goethite,
+    lizardite, maghemite, and quartz. The chemical composition of the ore indicates
+    that it is mainly composed of Fe2O3 (53.59%), followed by SiO2 (12.16%).
+  - The study on Azotobacter paspali bacteria in Iraq found that these bacteria have
+    a significant effect on fixing atmospheric nitrogen and dissolving phosphorus.
+    This is important in the context of biological fertilization of plants and soil,
+    which can reduce the need for synthetic fertilizers and potentially lower nitrogen
+    emissions that contribute to air pollution. In the environmental context, the
+    research on nitrogen dioxide air pollution in Madrid highlights the importance
+    of nitrogen compounds in air quality. The findings suggest that by promoting the
+    use of nitrogen-fixing bacteria in agriculture, we can reduce the reliance on
+    synthetic nitrogen fertilizers, which are a major source of nitrogen dioxide emissions.
+    This could lead to improved air quality and better human health protection. Future
+    research could focus on integrating these biological solutions with advanced air
+    pollution forecasting models to create a more holistic approach to managing nitrogen
+    in both agricultural and urban environments.
+  - In the Tigris River Batman-Hasankeyf region, intensive agricultural activities
+    are carried out, and irrigation is generally obtained from groundwater just as
+    it moves away from the riverfront. This region is a valuable basin for both Turkey
+    and the Middle East. A study using the Geographic Information System (GIS)-based
+    multicriteria decision-making (MCDM) analytic hierarchy process (AHP) was conducted
+    to explore the groundwater potential of the drainage area. The study considered
+    eight hydrological and hydrogeological criteria, including geomorphology, geology,
+    rainfall, drainage density, slope, lineament density, land use, and soil properties.
+    The major findings indicated that the groundwater-potential index values of the
+    basin were derived, and the groundwater potential zones were evaluated as very
+    poor (19%), poor (17%), moderate (34%), good (17%), and very good (13%).
+- source_sentence: How does the optical approach compare to the thermal approach in
+    mapping irrigated landcover, and what are the implications of this method?
+  sentences:
+  - The analysis of Land Use and Land Cover changes in Lagos State suggests that areas
+    with low flood hazard levels are less affected by the conversion of wetland areas
+    into developed areas and unplanned development. While wetland areas have significantly
+    decreased and developed areas have increased, the changes primarily impact very
+    high to moderate flood hazard zones.
+  - Managers and planners should focus on people’s perceptions and preferences of
+    park landscape characteristics to enhance the spatial vitality and services of
+    urban parks, ensuring they meet the needs of urban residents and visitors.
+  - The optical approach, which uses SWIR-transformed reflectance (STR), has been
+    found to be comparable to the thermal approach in mapping irrigated landcover.
+    Specifically, the classification accuracy of the optical approach was 97.6%, which
+    is slightly better than the 93.9% accuracy of the thermal approach. This confirms
+    the feasibility of using STR to map irrigated landcover, with broader implications
+    for the use of satellite imagery in these applications, potentially reducing the
+    reliance on microwave or thermal sensors.
+- source_sentence: Based on the Brine Shrimp Lethality Test (BSLT), what are the toxicity
+    levels of liquid smoke from cocoa pod skin at various pyrolysis temperatures and
+    water contents?
+  sentences:
+  - The estimated annual flood damage for agriculture and built-up areas in the Tajan
+    watershed, northern Iran, is projected to surge from USD 162 million to USD 376
+    million and USD 91 million to USD 220 million, respectively, by 2040, considering
+    the land use change scenarios from 2021 to 2040.
+  - 'The Brine Shrimp Lethality Test (BSLT) was used to determine the toxicity levels
+    of liquid smoke from cocoa pod skin at various pyrolysis temperatures and water
+    contents. The results showed that the LC50 values (the concentration required
+    to kill 50% of the test organisms) were as follows: at 200°C and 10% water content,
+    11,858.58 ppm; at 200°C and 15% water content, 13,094.23 ppm; at 200°C and 20%
+    water content, 13,373.94 ppm; at 200°C and 25% water content, 15,703.52 ppm. At
+    300°C and 10% water content, 11,604.26 ppm; at 300°C and 15% water content, 11,673.05
+    ppm; at 300°C and 20% water content, 13,373.94 ppm; at 300°C and 25% water content,
+    13,373.94 ppm. At 400°C and 10% water content, 9,213.73 ppm; at 400°C and 15%
+    water content, 13,094.237 ppm; at 400°C and 20% water content, 13,373.94 ppm;
+    at 400°C and 25% water content, 12,493.63 ppm. All the results indicate that the
+    liquid smoke from cocoa pod skin at different pyrolysis temperatures and water
+    contents is classified as non-toxic.'
+  - The distribution of PM2.5 in Santa Ana, CA, tends to be higher in socioeconomically
+    disadvantaged communities compared to other areas, highlighting environmental
+    health inequities that persist in urban areas. This can inform policy decisions
+    related to health equity and community access to resources.
+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). 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 c5cfa06e5e282a820e85d57f7fb053207494f41d -->
+- **Maximum Sequence Length:** 2048 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/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': 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("yasserrmd/geo-gemma-300m-emb")
+# Run inference
+queries = [
+    "Based on the Brine Shrimp Lethality Test (BSLT), what are the toxicity levels of liquid smoke from cocoa pod skin at various pyrolysis temperatures and water contents?",
+]
+documents = [
+    'The Brine Shrimp Lethality Test (BSLT) was used to determine the toxicity levels of liquid smoke from cocoa pod skin at various pyrolysis temperatures and water contents. The results showed that the LC50 values (the concentration required to kill 50% of the test organisms) were as follows: at 200°C and 10% water content, 11,858.58 ppm; at 200°C and 15% water content, 13,094.23 ppm; at 200°C and 20% water content, 13,373.94 ppm; at 200°C and 25% water content, 15,703.52 ppm. At 300°C and 10% water content, 11,604.26 ppm; at 300°C and 15% water content, 11,673.05 ppm; at 300°C and 20% water content, 13,373.94 ppm; at 300°C and 25% water content, 13,373.94 ppm. At 400°C and 10% water content, 9,213.73 ppm; at 400°C and 15% water content, 13,094.237 ppm; at 400°C and 20% water content, 13,373.94 ppm; at 400°C and 25% water content, 12,493.63 ppm. All the results indicate that the liquid smoke from cocoa pod skin at different pyrolysis temperatures and water contents is classified as non-toxic.',
+    'The estimated annual flood damage for agriculture and built-up areas in the Tajan watershed, northern Iran, is projected to surge from USD 162 million to USD 376 million and USD 91 million to USD 220 million, respectively, by 2040, considering the land use change scenarios from 2021 to 2040.',
+    'The distribution of PM2.5 in Santa Ana, CA, tends to be higher in socioeconomically disadvantaged communities compared to other areas, highlighting environmental health inequities that persist in urban areas. This can inform policy decisions related to health equity and community access to resources.',
+]
+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([[0.5805, 0.0253, 0.0709]])
+```
+
+<!--
+### 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: 41,432 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: 12 tokens</li><li>mean: 27.1 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 119.32 tokens</li><li>max: 413 tokens</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                             | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>How does plastic debris from land-based sources impact the ocean, particularly in the context of First Long Beach, China?</code>                                                 | <code>Plastic debris from land-based sources can significantly impact the ocean, as seen in the study conducted at First Long Beach (FLB), China. The study found that plastic debris amounts ranged from 2 to 82 particles per square meter on this marine sand beach. The most common size of plastics was 0.5–2.5 cm (44.4%), and the most common color was white (60.9%). The most abundant shape of plastic debris was fragments (76.2%). The amount of plastic debris varied significantly between different transects along the land-based source input zone due to the impacts of wind, ocean currents, and waves. Land-based wastewater discharge was identified as a major source of plastic debris on FLB, influenced by coastal water tide variations. Reduction strategies should focus on tracing and managing these land-based sources to mitigate the impact of plastic debris on the ocean.</code> |
+  | <code>How does the concentration of SO2 in urban areas of Nanjing correlate with the normalized difference vegetation index (NDVI), and what does this imply for public health?</code> | <code>The concentration of SO2 in urban areas of Nanjing exhibits a strong correlation (coefficient of determination, R2 > 0.5) with the normalized difference vegetation index (NDVI) within a radial distance of 2 km from the air pollutant monitoring sites. This indicates that NDVI can be an effective indicator for assessing the distribution and concentrations of air pollutants such as SO2. Negative correlations between NDVI and socio-economic indicators are observed under relatively consistent natural conditions, including climate and terrain. Therefore, the spatiotemporal distribution patterns of NDVI can provide valuable insights not only into socio-economic growth but also into the levels and locations of air pollution concentrations, which is crucial for public health interventions and policies.</code>                                                                   |
+  | <code>How has the rise of user-generated geodata impacted the role of traditional map producers?</code>                                                                                | <code>The rise of user-generated geodata has transformed ordinary citizens into neogeographers, blurring the boundaries between traditional map producers, such as national mapping agencies and local authorities, and citizens as consumers of this information. Citizens now actively participate in mapping different types of features on the Earth’s surface as volunteers, either by providing observations on the ground or tracing data from other sources, such as aerial photographs or satellite imagery. This has resulted in a significant increase in the availability of rich spatial datasets, which are often openly accessible through platforms like OpenStreetMap (OSM) and Ushahidi.</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
+
+- `num_train_epochs`: 1
+- `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`: 8
+- `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`: 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`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `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`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.0965 | 500  | 0.012         |
+| 0.1931 | 1000 | 0.006         |
+| 0.2896 | 1500 | 0.0057        |
+| 0.3862 | 2000 | 0.0045        |
+| 0.4827 | 2500 | 0.0024        |
+| 0.5793 | 3000 | 0.0013        |
+| 0.6758 | 3500 | 0.0025        |
+| 0.7723 | 4000 | 0.0029        |
+| 0.8689 | 4500 | 0.0012        |
+| 0.9654 | 5000 | 0.0004        |
+
+
+### Framework Versions
+- Python: 3.12.11
+- Sentence Transformers: 5.1.0
+- Transformers: 4.56.1
+- PyTorch: 2.8.0+cu128
+- Accelerate: 1.10.1
+- Datasets: 4.0.0
+- Tokenizers: 0.22.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### 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.*
+-->

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

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": 512,
+  "transformers_version": "4.56.1",
+  "use_bidirectional_attention": true,
+  "use_cache": true,
+  "vocab_size": 262144
+}

config_sentence_transformers.json

@@ -0,0 +1,26 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.1.0",
+    "transformers": "4.56.1",
+    "pytorch": "2.8.0+cu128"
+  },
+  "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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e046a30966b4d454c6e5106899029c3a03864c999b8a6c36631a5ad38b7d7ea
+size 1211486072

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"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 2048,
+    "do_lower_case": false
+}

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216e2a79606fe879c9f17c529c71cd241338407fd5646b595ffd3c4b9ea1d503
+size 33385262

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074