Feature Extraction
sentence-transformers
Safetensors
Transformers
English
mistraldual
sentence-similarity
custom_code
Instructions to use GeoGPT-Research-Project/GeoEmbedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use GeoGPT-Research-Project/GeoEmbedding with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("GeoGPT-Research-Project/GeoEmbedding", trust_remote_code=True) 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] - Transformers
How to use GeoGPT-Research-Project/GeoEmbedding with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="GeoGPT-Research-Project/GeoEmbedding", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("GeoGPT-Research-Project/GeoEmbedding", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
zhangzeqing commited on
Commit ·
29803c2
1
Parent(s): 0624635
add modelcard
Browse files
README.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# GeoEmbedding
|
| 2 |
The GeoEmbedding model is a geoscience-specific text embedding model built upon a high-performance large language model and fine-tuned on both general-purpose and in-domain geoscientific datasets. It produces accurate, context-aware vector representations of geoscientific texts, forming the backbone of vector-based retrieval in the RAG pipeline.
|
| 3 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
liscense:
|
| 5 |
+
- Apache 2.0
|
| 6 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
# GeoEmbedding
|
| 10 |
The GeoEmbedding model is a geoscience-specific text embedding model built upon a high-performance large language model and fine-tuned on both general-purpose and in-domain geoscientific datasets. It produces accurate, context-aware vector representations of geoscientific texts, forming the backbone of vector-based retrieval in the RAG pipeline.
|
| 11 |
|