Sentence Similarity
sentence-transformers
Safetensors
Transformers
ONNX
bert
feature-extraction
text-embeddings-inference
Instructions to use JayThinkDiff/CRE-0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use JayThinkDiff/CRE-0.5 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("JayThinkDiff/CRE-0.5") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use JayThinkDiff/CRE-0.5 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("JayThinkDiff/CRE-0.5") model = AutoModel.from_pretrained("JayThinkDiff/CRE-0.5") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,39 +9,47 @@ tags:
|
|
| 9 |
base_model:
|
| 10 |
- BAAI/bge-large-zh-v1.5
|
| 11 |
---
|
|
|
|
| 12 |
# CRE: CareerInternational Recruitment Embedding Model 🚀
|
|
|
|
| 13 |
> **CRE** 是一款专为人力资源场景打造的嵌入模型。通过引入局部特征感知(Local Feature-aware)的归纳偏好,显著提升了简历与职位描述(JD)的语义对齐精度。
|
|
|
|
| 14 |
---
|
|
|
|
| 15 |
### 💡 技术来源 (Technical Background)
|
|
|
|
| 16 |
| 维度 | 详细信息 |
|
| 17 |
| :--- | :--- |
|
| 18 |
| **专利名称** | 一种基于局部特征投影的招聘场景语义匹配方法及其系统 |
|
| 19 |
| **申请号** | 2025108424429 |
|
| 20 |
| **当前状态** | 已公开(实审中) |
|
| 21 |
| **主要发明人** | 焦英浩 等 |
|
|
|
|
| 22 |
---
|
| 23 |
|
| 24 |
### 更新日志 (Release Notes)
|
|
|
|
| 25 |
* **2025/03/28**: 发布 **CRE v0.5.0** 初始版本及技术报告。
|
| 26 |
-
|
| 27 |
### 核心特性 (Key Features)
|
| 28 |
* **局部特征提取 (Local Feature-aware)**: 借助 **CNN** 结构引入归纳偏好,使模型在文本编码过程中对人力资源场景下的“技能词”、“职级”等局部核心特征更为敏锐。
|
| 29 |
* **投影层设计 (Projection Layer)**: 本质上是一种精巧的辅助微调方法。通过在微调阶段增加特定的投影参数进行协同训练,在不破坏基座模型通用能力的前提下,大幅提高编码质量。
|
| 30 |
* **全场景覆盖**: 适配 **检索 (Retrieval)**、**RAG (检索增强生成)** 以及 **智能体 (Agent)** 等多种下游任务。
|
| 31 |
|
| 32 |
-
![CRE
|
| 33 |
|
| 34 |
### Using Sentence-Transformers
|
|
|
|
| 35 |
```python
|
| 36 |
-
from sentence_transformers import SentenceTransformer
|
| 37 |
-
from sentence_transformers import util
|
| 38 |
|
| 39 |
-
|
|
|
|
| 40 |
|
| 41 |
query_embedding = model.encode("嵌入式")
|
| 42 |
passage_embedding = model.encode([
|
| 43 |
-
"岗位职责:1.从事通讯产品相关嵌入式软件研发工作;2.进行软件详细设计
|
| 44 |
-
"招聘嵌入式系统工程师,要求会
|
| 45 |
])
|
| 46 |
|
| 47 |
print("查询结果:", util.cos_sim(query_embedding, passage_embedding))
|
|
@@ -52,14 +60,20 @@ Expected Output:
|
|
| 52 |
"""
|
| 53 |
```
|
| 54 |
|
| 55 |
-
<
|
| 56 |
-
|
| 57 |
-
|
|
|
|
|
|
|
| 58 |
</ul>
|
| 59 |
</small>
|
| 60 |
|
|
|
|
|
|
|
| 61 |
## Citation
|
|
|
|
| 62 |
If you find our work helpful, please cite this patent:
|
|
|
|
| 63 |
```bibtex
|
| 64 |
@misc{jiao2025recruitment,
|
| 65 |
title={一种基于局部特征投影的招聘场景语义匹配方法及其系统},
|
|
|
|
| 9 |
base_model:
|
| 10 |
- BAAI/bge-large-zh-v1.5
|
| 11 |
---
|
| 12 |
+
|
| 13 |
# CRE: CareerInternational Recruitment Embedding Model 🚀
|
| 14 |
+
|
| 15 |
> **CRE** 是一款专为人力资源场景打造的嵌入模型。通过引入局部特征感知(Local Feature-aware)的归纳偏好,显著提升了简历与职位描述(JD)的语义对齐精度。
|
| 16 |
+
|
| 17 |
---
|
| 18 |
+
|
| 19 |
### 💡 技术来源 (Technical Background)
|
| 20 |
+
|
| 21 |
| 维度 | 详细信息 |
|
| 22 |
| :--- | :--- |
|
| 23 |
| **专利名称** | 一种基于局部特征投影的招聘场景语义匹配方法及其系统 |
|
| 24 |
| **申请号** | 2025108424429 |
|
| 25 |
| **当前状态** | 已公开(实审中) |
|
| 26 |
| **主要发明人** | 焦英浩 等 |
|
| 27 |
+
|
| 28 |
---
|
| 29 |
|
| 30 |
### 更新日志 (Release Notes)
|
| 31 |
+
* **2026/05/09**: 发布 **CRE v1.1**,优化长文本特征提取与推理性能。
|
| 32 |
* **2025/03/28**: 发布 **CRE v0.5.0** 初始版本及技术报告。
|
| 33 |
+
|
| 34 |
### 核心特性 (Key Features)
|
| 35 |
* **局部特征提取 (Local Feature-aware)**: 借助 **CNN** 结构引入归纳偏好,使模型在文本编码过程中对人力资源场景下的“技能词”、“职级”等局部核心特征更为敏锐。
|
| 36 |
* **投影层设计 (Projection Layer)**: 本质上是一种精巧的辅助微调方法。通过在微调阶段增加特定的投影参数进行协同训练,在不破坏基座模型通用能力的前提下,大幅提高编码质量。
|
| 37 |
* **全场景覆盖**: 适配 **检索 (Retrieval)**、**RAG (检索增强生成)** 以及 **智能体 (Agent)** 等多种下游任务。
|
| 38 |
|
| 39 |
+

|
| 40 |
|
| 41 |
### Using Sentence-Transformers
|
| 42 |
+
|
| 43 |
```python
|
| 44 |
+
from sentence_transformers import SentenceTransformer, util
|
|
|
|
| 45 |
|
| 46 |
+
# 请根据实际发布的模型名修改
|
| 47 |
+
model = SentenceTransformer("JayThinkDiff/CRE-1.1")
|
| 48 |
|
| 49 |
query_embedding = model.encode("嵌入式")
|
| 50 |
passage_embedding = model.encode([
|
| 51 |
+
"岗位职责:1.从事通讯产品相关嵌入式软件研发工作;2.进行软件详细设计...",
|
| 52 |
+
"招聘嵌入式系统工程师,要求会设计嵌入式系统及单片机、会软件编程...",
|
| 53 |
])
|
| 54 |
|
| 55 |
print("查询结果:", util.cos_sim(query_embedding, passage_embedding))
|
|
|
|
| 60 |
"""
|
| 61 |
```
|
| 62 |
|
| 63 |
+
<small>
|
| 64 |
+
<strong>注意事项:</strong>
|
| 65 |
+
<ul>
|
| 66 |
+
<li>使用 CLS Token 来表征句子语义。</li>
|
| 67 |
+
<li>最大输入 Token 长度建议设置为 512。</li>
|
| 68 |
</ul>
|
| 69 |
</small>
|
| 70 |
|
| 71 |
+
---
|
| 72 |
+
|
| 73 |
## Citation
|
| 74 |
+
|
| 75 |
If you find our work helpful, please cite this patent:
|
| 76 |
+
|
| 77 |
```bibtex
|
| 78 |
@misc{jiao2025recruitment,
|
| 79 |
title={一种基于局部特征投影的招聘场景语义匹配方法及其系统},
|