Upload folder using huggingface_hub

README.md

@@ -1,179 +1,357 @@
 ---
-language: en
 tags:
 - sentence-transformers
-- food
-- embeddings
-- semantic-search
-- all-mpnet-base-v2
-library_name: sentence-transformers
-pipeline_tag: sentence-similarity
-license: mit
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:6010
+- loss:TripletLoss
+base_model: sentence-transformers/all-mpnet-base-v2
 widget:
-- source_sentence: Grilled chicken breast
+- source_sentence: Egg white, scrambled
+  sentences:
+  - Peaches, Frozen, Sliced, Sweetened
+  - Egg White Replacer, Loprofin
+  - Lemon, wedges (usually a garnish)
+- source_sentence: Crackers, saltines
   sentences:
-  - Roasted chicken breast
-  - Chicken thigh
-  - Salmon fillet
-- source_sentence: Fresh apple sliced
+  - Crackers, Saltines
+  - Crackers, Saltines, Whole Wheat
+  - Loops, Loprofin
+- source_sentence: Cereal, corn flakes
   sentences:
-  - Apple diced
-  - Apple juice
-  - Orange sliced
-- source_sentence: Greek yogurt plain
+  - Wheat Flour, Whole-Grain, Soft Wheat
+  - Cereals, Ralston Corn Flakes
+  - Sorghum Grain
+- source_sentence: Buffalo wings, hot sauce, celery
   sentences:
-  - Plain yogurt
-  - Vanilla yogurt
-  - Sour cream
-metrics:
-- pearson_cosine
-- spearman_cosine
-model-index:
-- name: Food Embeddings Model v2
-  results:
-  - task:
-      type: semantic-similarity
-      name: Food Description Semantic Similarity
-    dataset:
-      name: validation
-      type: validation
-    metrics:
-    - type: pearson_cosine
-      value: 0.9913
-      name: Pearson Cosine
-    - type: spearman_cosine
-      value: 0.9868
-      name: Spearman Cosine
+  - Caramel corn (some protein from corn, watch portion)
+  - Sauce, Hot Chile Sriracha
+  - Sauce, Hot Chile, Tuong Ot Sriracha Sriracha
+- source_sentence: Margarine, tub, light
+  sentences:
+  - Olive Oil
+  - Margarine, Smart Balance Light Buttery Spread
+  - Onions, Yellow Sauteed
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
 ---
 
-# Food Embeddings Model v2
+# SentenceTransformer based on sentence-transformers/all-mpnet-base-v2
 
-This is a [sentence-transformers](https://www.SBERT.net) model specialized for food description embeddings, fine-tuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). It maps food descriptions to a 768-dimensional dense vector space optimized for semantic food search, matching, and similarity comparison.
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2). 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:** sentence-transformers/all-mpnet-base-v2
+- **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) <!-- at revision 12e86a3c702fc3c50205a8db88f0ec7c0b6b94a0 -->
 - **Maximum Sequence Length:** 384 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': 384, 'do_lower_case': False}) with Transformer model: MPNetModel
-  (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})
+  (0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: MPNetModel 
+  (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): Normalize()
 )
 ```
 
-## Use Cases
-
-This model is optimized for:
-- Semantic food search
-- Food item matching and deduplication
-- Similar food recommendations
-- Vector database indexing for food catalogs
-- Nutritional analysis support
+## 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
 
-# Load model
-model = SentenceTransformer('jonny9f/food_embeddings2')
-
-# Generate embeddings
-food_description = "grilled chicken breast"
-embedding = model.encode(food_description)
+# Download from the 🤗 Hub
+model = SentenceTransformer("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'Margarine, tub, light',
+    'Margarine, Smart Balance Light Buttery Spread',
+    'Olive Oil',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
 
-# Use for similarity search, vector database indexing, etc.
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
 ```
 
-### Integration Example
+<!--
+### Direct Usage (Transformers)
 
-```python
-import numpy as np
-from sentence_transformers import SentenceTransformer
-from scipy.spatial.distance import cosine
+<details><summary>Click to see the direct usage in Transformers</summary>
 
-model = SentenceTransformer('jonny9f/food_embeddings2')
+</details>
+-->
 
-# Generate embeddings for multiple foods
-foods = [
-    "grilled chicken breast",
-    "roasted chicken breast",
-    "chicken thigh",
-    "salmon fillet"
-]
-embeddings = model.encode(foods)
+<!--
+### Downstream Usage (Sentence Transformers)
 
-# Compare similarities
-def get_similarity(emb1, emb2):
-    return 1 - cosine(emb1, emb2)
+You can finetune this model on your own dataset.
 
-# Print similarity matrix
-for i, food1 in enumerate(foods):
-    for j, food2 in enumerate(foods):
-        sim = get_similarity(embeddings[i], embeddings[j])
-        print(f"{food1} vs {food2}: {sim:.3f}")
-```
+<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
 
-### Model Training
-- **Training Framework:** sentence-transformers
-- **Training Mode:** Triplet Loss with self-supervision
-- **Dataset Size:** 1.2 million training samples
-- **Loss Function:** CosineSimilarityLoss with MSE
-- **Training Steps:** 37,500 per epoch
-- **Batch Size:** 32
-- **Training Time:** 3 epochs
-
-### Training Data
-The model was trained on carefully curated food description triplets:
-- Anchor: Base food description
-- Positive: Alternative description of the same food
-- Negative: Description of a different food
-- Self-supervision: For negative-only examples, anchor serves as its own positive
-
-### Performance
-
-Best validation metrics achieved:
-- **Pearson Cosine Correlation:** 0.9913
-- **Spearman Cosine Correlation:** 0.9868
-
-Training showed consistent improvement in loss values:
-- Initial Loss: ~0.0031
-- Final Loss: ~0.0004
-
-## Limitations and Biases
-
-- Model performance may vary for:
-  - Very long food descriptions
-  - Rare or unusual food items
-  - Highly technical nutritional terminology
-- Primary focus on English language descriptions
-- Best suited for standard food items and common variations
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 6,010 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>sentence_2</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                       | sentence_1                                                                       | sentence_2                                                                        |
+  |:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                           | string                                                                            |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 9.03 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 9.62 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 10.11 tokens</li><li>max: 23 tokens</li></ul> |
+* Samples:
+  | sentence_0                                            | sentence_1                                              | sentence_2                                                          |
+  |:------------------------------------------------------|:--------------------------------------------------------|:--------------------------------------------------------------------|
+  | <code>Green banana flour “meat” (experimental)</code> | <code>Green banana flour “meat” (experimental)</code>   | <code>Chicken Drumstick, Meat and Skin, Cooked, Fried, Flour</code> |
+  | <code>Carrot-ginger soup</code>                       | <code>Cauliflower Carrot Soup, the Secret Garden</code> | <code>Cream of Potato Soup, Canned, With Milk</code>                |
+  | <code>Milk, 2%</code>                                 | <code>Milk, 2%</code>                                   | <code>Milk, Whole 3.25% Milkfat, No Added Vitamins</code>           |
+* Loss: [<code>TripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#tripletloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
+      "triplet_margin": 5
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `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`: 16
+- `per_device_eval_batch_size`: 16
+- `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
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 1.3298 | 500  | 4.4921        |
+| 2.6596 | 1000 | 4.3269        |
+
+
+### Framework Versions
+- Python: 3.11.3
+- Sentence Transformers: 3.3.1
+- Transformers: 4.48.0
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.2.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
 
 ## Citation
 
-If you use this model, please cite:
+### 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",
+}
+```
+
+#### TripletLoss
 ```bibtex
-@software{food_embeddings2,
-  author = {Jon},
-  title = {Food Embeddings Model v2},
-  year = {2025},
-  publisher = {HuggingFace},
-  url = {https://huggingface.co/jonny9f/food_embeddings2}
+@misc{hermans2017defense,
+    title={In Defense of the Triplet Loss for Person Re-Identification},
+    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
+    year={2017},
+    eprint={1703.07737},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
 }
 ```
 
-## Framework Versions
-- Python: 3.11
-- Sentence Transformers: 2.2.2
-- PyTorch: 2.0.1
-- Transformers: 4.33.2
+<!--
+## 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.*
+-->