Push Phase 3 empire-embed sentence transformer

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 +1,413 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:333
+- loss:CosineSimilarityLoss
+base_model: sentence-transformers/all-MiniLM-L6-v2
+widget:
+- source_sentence: brain scan
+  sentences:
+  - 'Full WordPress Site Health Audit. Check plugins — installed, active, and update
+    status command Verify SEO configuration command Test page speed with Lighthouse
+    command Security check — WordFence scan and login protection check Test REST API
+    connectivity and credentials command Check Google Search Console for crawl errors
+    and ranking prompt. Tags: wordpress, audit, seo, security, performance, plugins,
+    health'
+  - 'Bulk Article Creation for a Site. Research topics and identify content gaps command
+    Generate content outlines and briefs command Write content using ZimmWriter or
+    scripts prompt Generate featured images for all articles command Publish articles
+    and set featured images command. Tags: content, articles, bulk, wordpress, seo,
+    publishing, zimmwriter'
+  - 'Run EMPIRE-BRAIN Scan and Intelligence Cycle. Run full empire brain scan command
+    Generate intelligence briefing command Check brain stats and performance metrics
+    command Run evolution cycle command Verify Sentinel service monitoring status
+    command. Tags: empire, brain, scan, intelligence, monitoring, evolution, briefing'
+- source_sentence: check vps
+  sentences:
+  - 'Cross-Site Internal Linking Strategy. Identify cluster and linking opportunities
+    check Find matching content between cluster sites command Generate and inject
+    cross-links command Verify and monitor link health command. Tags: seo, internal-links,
+    cross-site, clusters, link-whisper, revenue'
+  - 'Full WordPress Site Health Audit. Check plugins — installed, active, and update
+    status command Verify SEO configuration command Test page speed with Lighthouse
+    command Security check — WordFence scan and login protection check Test REST API
+    connectivity and credentials command Check Google Search Console for crawl errors
+    and ranking prompt. Tags: wordpress, audit, seo, security, performance, plugins,
+    health'
+  - 'Full WordPress Site Health Audit. Check plugins — installed, active, and update
+    status command Verify SEO configuration command Test page speed with Lighthouse
+    command Security check — WordFence scan and login protection check Test REST API
+    connectivity and credentials command Check Google Search Console for crawl errors
+    and ranking prompt. Tags: wordpress, audit, seo, security, performance, plugins,
+    health'
+- source_sentence: performance optim
+  sentences:
+  - 'Run EMPIRE-BRAIN Scan and Intelligence Cycle. Run full empire brain scan command
+    Generate intelligence briefing command Check brain stats and performance metrics
+    command Run evolution cycle command Verify Sentinel service monitoring status
+    command. Tags: empire, brain, scan, intelligence, monitoring, evolution, briefing'
+  - 'Site Speed & Core Web Vitals Optimization. Run Lighthouse audit command Configure
+    LiteSpeed Cache (all sites use it) command Image optimization check Font and render-blocking
+    resource optimization check Verify improvements and monitor command. Tags: seo,
+    speed, performance, core-web-vitals, litespeed, images, caching'
+  - 'WordPress Plugin Deployment to Sites. Check if plugin is available on WorldPressIT
+    check Install via WordPress REST API or WP-CLI command Configure plugin settings
+    prompt Verify no conflicts with existing plugins check Deploy fleet-wide if applicable
+    prompt. Tags: wordpress, plugin, deploy, fleet'
+- source_sentence: make pinterest pin
+  sentences:
+  - 'Generate Article Featured Images. Run article_images_pipeline.py with correct
+    arguments command Verify the featured image was set check. Tags: content, images,
+    wordpress, featured-image'
+  - 'Social Media Post Generation & Scheduling. Generate platform-specific images
+    command Write platform-specific copy prompt Schedule or post via automation command.
+    Tags: content, social, pinterest, instagram, facebook, twitter, scheduling'
+  - 'Bootstrap a New Empire Project. Create project directory and initialize git command
+    Create PROJECT_DNA.md command Create CLAUDE.md with project-specific config prompt
+    Set up Python environment command Create initial git commit and push to GitHub
+    command Register project in EMPIRE-BRAIN command. Tags: empire, project, bootstrap,
+    setup, new'
+- source_sentence: batch articles
+  sentences:
+  - 'Bulk Article Creation for a Site. Research topics and identify content gaps command
+    Generate content outlines and briefs command Write content using ZimmWriter or
+    scripts prompt Generate featured images for all articles command Publish articles
+    and set featured images command. Tags: content, articles, bulk, wordpress, seo,
+    publishing, zimmwriter'
+  - 'Site Speed & Core Web Vitals Optimization. Run Lighthouse audit command Configure
+    LiteSpeed Cache (all sites use it) command Image optimization check Font and render-blocking
+    resource optimization check Verify improvements and monitor command. Tags: seo,
+    speed, performance, core-web-vitals, litespeed, images, caching'
+  - 'SSL Certificate & Domain Management. Check domain/SSL status via Hostinger command
+    Manage DNS records command SSL certificate management manual Domain security audit
+    command. Tags: ssl, domain, certificate, dns, hostinger, renewal'
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: empire eval
+      type: empire-eval
+    metrics:
+    - type: pearson_cosine
+      value: 0.5531234570199464
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.5320495924169611
+      name: Spearman Cosine
+---
+
+# 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("WealthFromAI/empire-embed")
+# Run inference
+sentences = [
+    'batch articles',
+    'Bulk Article Creation for a Site. Research topics and identify content gaps command Generate content outlines and briefs command Write content using ZimmWriter or scripts prompt Generate featured images for all articles command Publish articles and set featured images command. Tags: content, articles, bulk, wordpress, seo, publishing, zimmwriter',
+    'Site Speed & Core Web Vitals Optimization. Run Lighthouse audit command Configure LiteSpeed Cache (all sites use it) command Image optimization check Font and render-blocking resource optimization check Verify improvements and monitor command. Tags: seo, speed, performance, core-web-vitals, litespeed, images, caching',
+]
+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, 0.7041, 0.2289],
+#         [0.7041, 1.0000, 0.3787],
+#         [0.2289, 0.3787, 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.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Dataset: `empire-eval`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| pearson_cosine      | 0.5531    |
+| **spearman_cosine** | **0.532** |
+
+<!--
+## 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: 333 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 333 samples:
+  |         | sentence_0                                                                       | sentence_1                                                                         | label                                                          |
+  |:--------|:---------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------|
+  | type    | string                                                                           | string                                                                             | float                                                          |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 5.24 tokens</li><li>max: 33 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 62.94 tokens</li><li>max: 141 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.57</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence_0                     | sentence_1                                                                                                                                                                                                                                                                                                                                                                                                                              | label            |
+  |:-------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>bootstrap project</code> | <code>Bootstrap a New Empire Project. Create project directory and initialize git command Create PROJECT_DNA.md command Create CLAUDE.md with project-specific config prompt Set up Python environment command Create initial git commit and push to GitHub command Register project in EMPIRE-BRAIN command. Tags: empire, project, bootstrap, setup, new</code>                                                                       | <code>1.0</code> |
+  | <code>update container</code>  | <code>WordPress Site SEO Setup & Configuration. Verify RankMath SEO plugin is installed and activated check Configure RankMath general settings prompt Set up Schema markup patterns per post type prompt Configure robots.txt and sitemap command Set up internal linking structure prompt Configure affiliate link handling prompt. Tags: wordpress, seo, rankmath, schema, setup</code>                                              | <code>0.0</code> |
+  | <code>restart service</code>   | <code>Full WordPress Site Health Audit. Check plugins — installed, active, and update status command Verify SEO configuration command Test page speed with Lighthouse command Security check — WordFence scan and login protection check Test REST API connectivity and credentials command Check Google Search Console for crawl errors and ranking prompt. Tags: wordpress, audit, seo, security, performance, plugins, health</code> | <code>0.0</code> |
+* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
+  ```json
+  {
+      "loss_fct": "torch.nn.modules.loss.MSELoss"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 16
+- `num_train_epochs`: 5
+- `eval_strategy`: steps
+- `per_device_eval_batch_size`: 16
+- `multi_dataset_batch_sampler`: round_robin
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `per_device_train_batch_size`: 16
+- `num_train_epochs`: 5
+- `max_steps`: -1
+- `learning_rate`: 5e-05
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: None
+- `warmup_steps`: 0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `optim_target_modules`: None
+- `gradient_accumulation_steps`: 1
+- `average_tokens_across_devices`: True
+- `max_grad_norm`: 1
+- `label_smoothing_factor`: 0.0
+- `bf16`: False
+- `fp16`: False
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `use_cache`: False
+- `neftune_noise_alpha`: None
+- `torch_empty_cache_steps`: None
+- `auto_find_batch_size`: False
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `include_num_input_tokens_seen`: no
+- `log_level`: passive
+- `log_level_replica`: warning
+- `disable_tqdm`: False
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `eval_strategy`: steps
+- `per_device_eval_batch_size`: 16
+- `prediction_loss_only`: True
+- `eval_on_start`: False
+- `eval_do_concat_batches`: True
+- `eval_use_gather_object`: False
+- `eval_accumulation_steps`: None
+- `include_for_metrics`: []
+- `batch_eval_metrics`: False
+- `save_only_model`: False
+- `save_on_each_node`: False
+- `enable_jit_checkpoint`: False
+- `push_to_hub`: False
+- `hub_private_repo`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_always_push`: False
+- `hub_revision`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `restore_callback_states_from_checkpoint`: False
+- `full_determinism`: False
+- `seed`: 42
+- `data_seed`: None
+- `use_cpu`: False
+- `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
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `dataloader_prefetch_factor`: None
+- `remove_unused_columns`: True
+- `label_names`: None
+- `train_sampling_strategy`: random
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `ddp_backend`: None
+- `ddp_timeout`: 1800
+- `fsdp`: []
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `deepspeed`: None
+- `debug`: []
+- `skip_memory_metrics`: True
+- `do_predict`: False
+- `resume_from_checkpoint`: None
+- `warmup_ratio`: None
+- `local_rank`: -1
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch | Step | empire-eval_spearman_cosine |
+|:-----:|:----:|:---------------------------:|
+| 1.0   | 21   | 0.5320                      |
+
+
+### Framework Versions
+- Python: 3.12.10
+- Sentence Transformers: 5.3.0
+- Transformers: 5.4.0
+- PyTorch: 2.11.0+cpu
+- Accelerate: 1.13.0
+- Datasets: 4.8.4
+- Tokenizers: 0.22.2
+
+## 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.*
+-->

config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "is_decoder": false,
+  "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.4.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "5.4.0",
+    "pytorch": "2.11.0+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:d3e31ef7a5a0e3061aee0d093494ae196d535090c70373a7a89b22f1149fb6ed
+size 90864176

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
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": true,
+  "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]"
+}