初始化项目，由ModelHub XC社区提供模型

Model: disham993/electrical-embeddinggemma-ir_finetune_16bit
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+eeir-models-retrieval-comparison.png filter=lfs diff=lfs merge=lfs -text
+poster.png 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 sha256:1a96e74fabcdf6b81dc67562b923e9f9c6ab4a0b7e75d1a2a705debfd0d704b1
+size 4718680

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:e52d25716b14b0cf5142e1743dee3d5caeef0b42d4567ec510124cdb2896ca49
+size 4718680

README.md

@@ -0,0 +1,164 @@
+---
+language:
+- en
+library_name: sentence-transformers
+pipeline_tag: feature-extraction
+base_model: unsloth/embeddinggemma-300m
+datasets:
+- disham993/ElectricalElectronicsIR
+tags:
+- embedding
+- retrieval
+- electrical-engineering
+- unsloth
+- safetensors
+- sentence-transformers
+- information-retrieval
+- rag
+- semantic-search
+- arxiv:2509.20354
+license: mit
+---
+
+# electrical-embeddinggemma-ir_finetune_16bit
+
+## Model Description
+
+This model is a **fully merged fp16 checkpoint** fine-tuned from [`unsloth/embeddinggemma-300m`](https://huggingface.co/unsloth/embeddinggemma-300m) — Unsloth's optimized mirror of Google's [EmbeddingGemma-300M](https://huggingface.co/google/embeddinggemma-300m) — for feature-extraction tasks, specifically dense Information Retrieval (IR) in the electrical and electronics engineering domain. The LoRA adapter weights have been merged into the base model and saved as full fp16 `.safetensors` weights, making this the most compatible variant for the Hugging Face ecosystem (Sentence Transformers, vLLM, Text Embeddings Inference, etc.).
+
+This repository contains the complete model weights (~1.2 GB) and does **not** require a `llama.cpp` backend.
+
+<p align="center"><img src="https://huggingface.co/disham993/electrical-embeddinggemma-ir_finetune_16bit/resolve/main/poster.png" width="340"/></p>
+
+## Training Data
+
+The model was trained on the [`disham993/ElectricalElectronicsIR`](https://huggingface.co/datasets/disham993/ElectricalElectronicsIR) dataset — 20,000 question-passage pairs covering electrical engineering, electronics, power systems, and communications.
+
+- **16k train / 2k validation / 2k test**
+- Queries: 133–822 characters; passages: 586–5,590 characters
+- Topics include phased array antennas, IEC 61850 protocols, Josephson junctions, OTDR measurements, MIMO channel estimation, FPGA partial reconfiguration, and more
+
+## Model Details
+
+| | |
+|---|---|
+| **Base Model** | `unsloth/embeddinggemma-300m` (308M params) |
+| **Format** | Merged fp16 (`.safetensors`) |
+| **Task** | Feature Extraction (Dense IR / Semantic Search) |
+| **Language** | English (en) |
+| **Dataset** | `disham993/ElectricalElectronicsIR` |
+| **Model size** | ~1.2 GB |
+| **License** | MIT |
+
+## Training Procedure
+
+### Training Hyperparameters
+
+| | |
+|---|---|
+| **Method** | LoRA via Unsloth's `FastSentenceTransformer`, merged to fp16 |
+| **LoRA rank / alpha** | r=32, α=64 |
+| **Target modules** | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
+| **Loss** | `MultipleNegativesRankingLoss` (in-batch negatives) |
+| **Batch size** | 128 per device × 2 gradient accumulation = 256 effective |
+| **Learning rate** | 2e-5 (linear schedule, 3% warmup) |
+| **Max steps** | 100 |
+| **Max sequence length** | 1024 |
+| **Precision** | bf16 (training) → fp16 (saved) |
+| **Batch sampler** | `NO_DUPLICATES` |
+| **Hardware** | NVIDIA RTX 5090 |
+
+## Evaluation Results
+
+Evaluated on the held-out test split (2,000 queries) of `disham993/ElectricalElectronicsIR` using `sentence_transformers.evaluation.InformationRetrievalEvaluator`.
+
+| Model | MAP@100 | NDCG@10 | MRR@10 | Recall@10 |
+|---|---|---|---|---|
+| `unsloth/embeddinggemma-300m` (baseline) | 0.5753 | 0.6221 | 0.5682 | 0.7925 |
+| `electrical-embeddinggemma-ir_lora` | 0.9795 | 0.9847 | 0.9795 | 1.0000 |
+| **`electrical-embeddinggemma-ir_finetune_16bit` (this model)** | **0.9797** | **0.9849** | **0.9797** | **1.0000** |
+| `electrical-embeddinggemma-ir_f16` | 0.9849 | 0.9887 | 0.9849 | 0.9995 |
+| `electrical-embeddinggemma-ir_q8_0` | 0.9844 | 0.9883 | 0.9844 | 0.9995 |
+| `electrical-embeddinggemma-ir_q4_k_m` | 0.9841 | 0.9879 | 0.9840 | 0.9990 |
+| `electrical-embeddinggemma-ir_q5_k_m` | 0.9824 | 0.9866 | 0.9823 | 0.9990 |
+
+**+41 pp MAP@100 and +73% relative MRR@10 improvement over the general-purpose baseline. Recall@10 = 1.0000 — perfect top-10 coverage.**
+
+## Usage
+
+```bash
+# Install dependencies
+pip install sentence-transformers torch
+```
+
+```python
+import torch
+import torch.nn.functional as F
+from sentence_transformers import SentenceTransformer
+
+# === SEMANTIC SEARCH EXAMPLE ===
+if __name__ == "__main__":
+    print("Downloading and Booting Engine...")
+    
+    # SentenceTransformers flawlessly supports this repository natively!
+    model = SentenceTransformer("disham993/electrical-electronics-gemma-ir_finetune_16bit")
+    
+    query = "How do transformers step up voltage?"
+    
+    # A miniature corpus of engineering documents
+    documents = [
+        "Ohm's law defines the relationship between voltage, current, and resistance.",
+        "AC circuits use alternating current which changes direction periodically.",
+        "A step-up transformer has more turns on its secondary coil than its primary, increasing voltage.",
+        "Capacitors store electrical energy in an electric field.",
+        "Inductors resist changes in electric current passing through them.",
+        "Transformers operate on Faraday's law of induction to transfer energy between circuits.",
+        "Diodes allow current to pass in only one direction.",
+        "Voltage is the electric potential difference between two points."
+    ]
+    
+    print("Extracting Embeddings...")
+    # Convert texts directly to PyTorch tensors
+    query_emb = model.encode(query, convert_to_tensor=True)
+    doc_embs = model.encode(documents, convert_to_tensor=True)
+    
+    # Calculate similarities natively 
+    similarities = F.cosine_similarity(query_emb.unsqueeze(0), doc_embs)
+    
+    # Retrieve the top 3 highest scoring documents
+    top_3_idx = torch.topk(similarities, k=3).indices.tolist()
+    
+    print(f"\n--- Top 3 Documents for Query: '{query}' ---")
+    for rank, idx in enumerate(top_3_idx, 1):
+        print(f"Rank {rank} (Score: {similarities[idx]:.4f}) | {documents[idx]}")
+```
+
+## Limitations and Bias
+
+While this model performs exceptionally well in the electrical and electronics engineering domain, it is not designed for use in other domains. Additionally, it may:
+
+- Underperform on queries that mix electrical engineering with unrelated domains (e.g., biomedical, legal, financial)
+- Show reduced performance on non-English text or highly colloquial phrasing
+- Be slower and more memory-intensive than the GGUF variants (~1.2 GB vs ~236 MB for q4_k_m)
+
+This model is intended for research, educational, and production IR applications in the electrical engineering domain.
+
+## Training Infrastructure
+
+For the complete fine-tuning and evaluation pipeline — from data loading to GGUF export — refer to the [GitHub repository](https://github.com/di37/electrical-embeddinggemma-ir-finetuning-evaluation) and the notebooks `Finetuning_EmbeddingGemma_EEIR_RTX_5090.ipynb` and `Evaluate_All_Models.ipynb`.
+
+## Last Update
+
+2026-04-18
+
+## Citation
+
+```bibtex
+@misc{electrical-embeddinggemma-ir,
+  author       = {disham993},
+  title        = {Electrical \& Electronics Engineering Embedding Models},
+  year         = {2026},
+  howpublished = {\url{https://huggingface.co/collections/disham993/electrical-and-electronics-engineering-embedding-models}},
+}
+```
+

added_tokens.json

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

config.json

@@ -0,0 +1,62 @@
+{
+    "_sliding_window_pattern": 6,
+    "architectures": [
+        "Gemma3TextModel"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "torch_dtype": "bfloat16",
+    "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_name": "unsloth/embeddinggemma-300m",
+    "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,
+    "tokenizer_class": "GemmaTokenizerFast",
+    "unsloth_version": "2026.4.6",
+    "use_bidirectional_attention": true,
+    "use_cache": true,
+    "vocab_size": 262144
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "4.56.2",
+    "pytorch": "2.10.0+cu128"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

eeir-models-retrieval-comparison.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4c5292f17104668aaefe797397515f723c31a4a5c24b7d3e824996c5834605
+size 100559

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd2fb3fe8231cef44e800759736a9a282c40b3d2278fe127578a7bd45287c74
+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"
+  }
+]

poster.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322e1f2a54f78bde72c68c1ba597802cc43ea8dfee6b86202eeabfecb5c9d06f
+size 379748

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 sha256:45732ebfacbc3b3da71bd8290d8c14c0df3b2d8d63d86970a953c59d71bd36d8
+size 33385261

tokenizer.model

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