初始化项目，由ModelHub XC社区提供模型

Model: llm-semantic-router/aegis-embed
Source: Original Platform

.gitattributes

@@ -0,0 +1,40 @@
+*.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
+onnx/layer-11/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/layer-16/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/layer-22/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/layer-6/model.onnx.data 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
+}

README.md

@@ -0,0 +1,308 @@
+---
+library_name: sentence-transformers
+tags:
+  - sentence-transformers
+  - sentence-similarity
+  - feature-extraction
+  - embeddings
+  - multilingual
+  - matryoshka
+  - 2d-matryoshka
+  - long-context
+  - modernbert
+  - retrieval
+  - rag
+  - agents
+  - routing
+  - memory
+base_model: llm-semantic-router/mmbert-32k-yarn
+datasets:
+  - BAAI/bge-m3-data
+language:
+  - multilingual
+license: apache-2.0
+pipeline_tag: sentence-similarity
+model-index:
+  - name: aegis-embed
+    results:
+      - task:
+          type: STS
+        dataset:
+          name: STS Benchmark
+          type: mteb/stsbenchmark-sts
+        metrics:
+          - type: spearman
+            value: 80.5
+---
+
+# aegis-embed
+
+`aegis-embed` is a **multilingual long-context embedding model purpose-built for agent-native retrieval, memory, and decision workflows**.
+
+It is designed for systems where embeddings sit on the semantic hot path rather than at the edge of the stack: **memory lookup, knowledge retrieval, tool matching, task routing, long-horizon recall, clustering, and multilingual indexing**. Its value is not just a benchmark score, but a practical operating profile that fits real agent runtimes: **32K context**, **2D Matryoshka adaptability across dimensions and layers**, **307M-class deployability**, and **strong latency-quality efficiency under repeated inference**.
+
+In short, `aegis-embed` is built for teams that want one embedding space to support **fast routing, scalable retrieval, and high-confidence semantic matching** without paying the operational cost of a much larger model.
+
+## Why it fits agentic workloads
+
+Agentic systems do not call embeddings once. They call them **everywhere**: before retrieval, during routing, when matching tools, when searching memory, and while compressing or re-ranking state. That means a useful agent embedding model must be more than accurate — it must also be flexible under tight runtime budgets.
+
+`aegis-embed` is designed around that reality.
+
+### 1. One model, many budget tiers
+
+This model supports **Matryoshka embeddings**, which means you can encode once at full size and truncate to smaller dimensions with limited quality loss.
+
+That is especially useful for agent systems because different stages of the stack often need different budgets:
+
+- **64d** for very cheap candidate generation, broad routing, or huge memory banks
+- **256d** for balanced retrieval over large corpora
+- **768d** for highest-quality retrieval, offline indexing, or final-stage matching
+
+Instead of managing separate embedding models for each tier, you can keep **one semantic space** and choose the dimensional budget that matches the task.
+
+### 2. 2D Matryoshka gives runtime flexibility, not just storage savings
+
+The model is trained with **2D Matryoshka** behavior:
+
+- **dimension reduction** for smaller vectors and lower storage / bandwidth cost
+- **layer reduction** for lower-latency inference paths in custom runtimes
+
+This matters for agents because the same system often mixes:
+
+- latency-sensitive routing decisions
+- high-volume memory scans
+- higher-quality retrieval for final evidence gathering
+
+A single model that can serve multiple latency / quality profiles is much easier to operate than a stack of unrelated specialized encoders.
+
+### 3. Long context helps when agent state is not naturally short
+
+Many agent workloads are not short isolated queries. They involve:
+
+- tool descriptions
+- execution traces
+- long notes
+- merged memory summaries
+- multi-hop research snippets
+- large document chunks
+
+With **32,768 tokens** of context length, `aegis-embed` can represent larger semantic units before you are forced into aggressive chunking. That helps preserve cross-section meaning in long documents and richer memory entries.
+
+### 4. Small enough to be operationally practical
+
+At roughly **307M parameters**, this model sits in a useful middle ground:
+
+- substantially lighter than large embedding models in the 600M+ or multi-billion range
+- still expressive enough for multilingual retrieval and similarity work
+- easier to host in systems where embedding is part of a hot path rather than an occasional offline batch
+
+For agentic platforms, that usually means better economics and simpler scaling.
+
+### 5. One embedding space across the stack
+
+Agent systems are easier to operate when **routing, retrieval, memory search, and semantic matching** all live in the same vector space.
+
+`aegis-embed` is well suited to that pattern:
+
+- **64d** can serve broad routing and large-memory scanning
+- **256d** can cover the main retrieval tier
+- **768d** can stay reserved for the highest-fidelity matching paths
+
+That means one model can cover multiple semantic stages without forcing the system to juggle incompatible encoders, duplicated indexes, or divergent retrieval behavior.
+
+## Model at a glance
+
+| Feature | Value |
+|---------|-------|
+| **Parameters** | 307M |
+| **Architecture** | ModernBERT encoder with YaRN scaling |
+| **Hidden Size** | 768 |
+| **Layers** | 22 |
+| **Context Length** | 32,768 tokens |
+| **Pooling** | Mean pooling |
+| **Similarity** | Cosine |
+| **Languages** | Multilingual |
+| **Matryoshka Dimensions** | 768, 512, 256, 128, 64 |
+
+## Headline results
+
+| Metric | Score |
+|--------|-------|
+| **MTEB Mean (24 tasks)** | **61.4** |
+| **STS Benchmark** | **80.5** |
+| **Dimension Retention** | **99% @ 256d**, **98% @ 64d** |
+| **Layer Speedup** | **3.3× @ 6L**, **5.8× @ 3L** |
+| **Latency vs BGE-M3** | **1.6-3.1× faster** on longer sequences / larger batches |
+
+These numbers make the model particularly attractive for systems that must balance **quality, latency, vector size, and deployment simplicity** instead of optimizing only for leaderboard peak score.
+
+## Usage
+
+### Basic usage with Sentence Transformers
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("/path/to/aegis-embed")
+
+texts = [
+    "Find tool descriptions related to browser automation.",
+    "检索和用户历史偏好相关的记忆。",
+    "Retrieve notes about deployment failures in staging.",
+]
+
+embeddings = model.encode(texts)
+print(embeddings.shape)  # (3, 768)
+```
+
+### Matryoshka truncation for smaller vectors
+
+```python
+import torch.nn.functional as F
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("/path/to/aegis-embed")
+embeddings = model.encode(texts, convert_to_tensor=True)
+
+# Balanced retrieval tier
+embeddings_256d = F.normalize(embeddings[:, :256], p=2, dim=1)
+
+# Ultra-cheap routing / large memory-bank tier
+embeddings_64d = F.normalize(embeddings[:, :64], p=2, dim=1)
+```
+
+### Long-context encoding
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("/path/to/aegis-embed")
+model.max_seq_length = 8192  # can be increased up to 32768
+
+long_note = "..."
+embedding = model.encode(long_note)
+```
+
+## Why Matryoshka matters for agents
+
+A common agent stack has several retrieval-like stages:
+
+1. **broad candidate fetch** over a very large store
+2. **narrower semantic lookup** over a smaller candidate set
+3. **high-confidence final matching** before action or answer synthesis
+
+Matryoshka lets one model support all three stages:
+
+| Stage | Suggested Dim | Why |
+|------|---------------|-----|
+| Broad routing / candidate generation | 64d | Maximize speed and minimize storage |
+| Main retrieval | 256d | Strong balance of quality and cost |
+| Final matching / offline indexing | 768d | Best semantic fidelity |
+
+That is often a better operational story than mixing several incompatible embedding models across the same pipeline.
+
+## Evaluation details
+
+### MTEB benchmark (24 tasks)
+
+| Category | Score |
+|----------|-------|
+| STS (7 tasks) | **79.3** |
+| Classification (6) | 62.4 |
+| Pair Classification (2) | 76.2 |
+| Reranking (2) | 64.4 |
+| Clustering (4) | 36.9 |
+| Retrieval (3) | 38.2 |
+| **Overall Mean** | **61.4** |
+
+### STS benchmark comparison
+
+| Model | Parameters | STS Score |
+|-------|------------|-----------|
+| Qwen3-Embed-0.6B | 600M | 76.17 |
+| **aegis-embed** | **307M** | **80.5** |
+| Qwen3-Embed-8B | 8B | 81.08 |
+
+### 2D Matryoshka quality matrix (STS)
+
+| Layers | 768d | 256d | 64d |
+|--------|------|------|-----|
+| 22L | **80.5** | 79.9 | 78.5 |
+| 11L | 53.7 | 48.0 | 44.4 |
+| 6L | 45.2 | 45.2 | 43.5 |
+| 3L | 44.0 | 44.1 | 41.8 |
+
+### Long-context retrieval (4K tokens)
+
+| Metric | Score |
+|--------|-------|
+| R@1 | 68.8% |
+| R@10 | 81.2% |
+| MRR | 71.9% |
+
+### Throughput (AMD MI300X)
+
+| Layers | Throughput | Speedup |
+|--------|------------|---------|
+| 22L | 477/s | 1.0× |
+| 11L | 916/s | 1.9× |
+| 6L | 1573/s | 3.3× |
+| 3L | 2761/s | 5.8× |
+
+## Training
+
+### Data
+
+Trained on [BAAI/bge-m3-data](https://huggingface.co/datasets/BAAI/bge-m3-data) with multilingual triplets across diverse domains.
+
+### Configuration
+
+- **Base model**: [llm-semantic-router/mmbert-32k-yarn](https://huggingface.co/llm-semantic-router/mmbert-32k-yarn)
+- **Loss**: `Matryoshka2dLoss` (combines adaptive layer loss and Matryoshka loss)
+- **Matryoshka dimensions**: `[768, 512, 256, 128, 64]`
+- **Max sequence length**: `32768`
+- **Batch size**: `16` (effective `32` with gradient accumulation)
+- **Learning rate**: `2e-5`
+- **Hardware**: AMD Instinct MI300X
+
+## Recommended use cases
+
+`aegis-embed` is especially well suited for:
+
+- **Agent memory retrieval** across long, mixed-format notes or histories
+- **Tool and skill selection** where descriptions need semantic matching
+- **Knowledge-base retrieval** for assistants and RAG systems
+- **Multilingual search** across mixed-language corpora
+- **Large memory banks** that benefit from 64d / 256d vector tiers
+- **Long-document semantic indexing** where short-context encoders lose structure
+
+## Model lineage and packaging
+
+`aegis-embed` is derived from `llm-semantic-router/mmbert-embed-32k-2d-matryoshka` and distributed here as a lean Sentence Transformers / PyTorch package.
+
+This build intentionally omits bundled ONNX artifacts so the model remains smaller and easier to move, mirror, cache, and deploy in environments that primarily rely on native Transformers runtimes.
+
+## Limitations
+
+- Full-quality mode is still the best default for important retrieval decisions; aggressive layer reduction trades away quality.
+- Although the model supports up to 32K tokens, very long inputs still increase compute and memory cost.
+- The model is optimized for retrieval and semantic similarity; some downstream tasks may benefit from task-specific fine-tuning.
+- If your deployment stack requires ONNX out of the box, you will need to export that separately.
+
+## Citation
+
+If you use this model, please cite the upstream work it is derived from:
+
+```bibtex
+@misc{mmbert-embed-2d-matryoshka,
+  title={mmBERT-Embed: Multilingual Embedding Model with 2D Matryoshka Training},
+  author={vLLM Semantic Router Team},
+  year={2025},
+  url={https://huggingface.co/llm-semantic-router/mmbert-embed-32k-2d-matryoshka}
+}
+```
+
+## License
+
+Apache 2.0

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 1,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "bfloat16",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 1,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 160000,
+  "mask_token_id": 4,
+  "max_position_embeddings": 32768,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 0,
+  "position_embedding_type": "sans_pos",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 1,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "transformers_version": "4.57.6",
+  "vocab_size": 256000
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.3.0.dev0",
+    "transformers": "4.57.6",
+    "pytorch": "2.9.1+git8907517"
+  },
+  "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 sha256:173eb71beab911ddccf5c23d46129890894f1b741bedbf15e6d0f46084da3391
+size 613892480

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 32768,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,55 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<eos>",
+    "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 sha256:5b14c7584d507951e1723f53f4e82cc76db81b7c0df3dc3c48bed45954b0277c
+size 34363443