Feature Extraction
sentence-transformers
Safetensors
Chinese
bert
meteorology
domain-adaptive
contrastive-learning
retrieval
embedding
text-embeddings-inference
Instructions to use nmcsitian/bge-meteo-zh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use nmcsitian/bge-meteo-zh with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("nmcsitian/bge-meteo-zh") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -29,7 +29,7 @@ BGE-Meteo-zh 是基于 [BAAI/bge-large-zh-v1.5](https://huggingface.co/BAAI/bge-
|
|
| 29 |
- **训练数据**: 58本气象专业书籍合成的6,868条QA数据,每条配7个BM25困难负例
|
| 30 |
- **防泄露设计**: 训练专用BM25索引严格排除held-out测试书籍,防止负例毒化
|
| 31 |
- **训练配置**: batch_size=4, train_group_size=8, lr=1e-5, 3 epochs, BF16
|
| 32 |
-
- **训练硬件**: 单卡NVIDIA RTX 4080 (16GB)
|
| 33 |
|
| 34 |
## 性能指标
|
| 35 |
|
|
|
|
| 29 |
- **训练数据**: 58本气象专业书籍合成的6,868条QA数据,每条配7个BM25困难负例
|
| 30 |
- **防泄露设计**: 训练专用BM25索引严格排除held-out测试书籍,防止负例毒化
|
| 31 |
- **训练配置**: batch_size=4, train_group_size=8, lr=1e-5, 3 epochs, BF16
|
| 32 |
+
- **训练硬件**: 单卡NVIDIA RTX 4080 (16GB)
|
| 33 |
|
| 34 |
## 性能指标
|
| 35 |
|