Update README.md
Browse files
README.md
CHANGED
|
@@ -1,79 +1,83 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: sentence-transformers/all-MiniLM-L6-v2
|
| 3 |
-
datasets:
|
| 4 |
-
- s2orc
|
| 5 |
-
- flax-sentence-embeddings/stackexchange_xml
|
| 6 |
-
- ms_marco
|
| 7 |
-
- gooaq
|
| 8 |
-
- yahoo_answers_topics
|
| 9 |
-
- code_search_net
|
| 10 |
-
- search_qa
|
| 11 |
-
- eli5
|
| 12 |
-
- snli
|
| 13 |
-
- multi_nli
|
| 14 |
-
- wikihow
|
| 15 |
-
- natural_questions
|
| 16 |
-
- trivia_qa
|
| 17 |
-
- embedding-data/sentence-compression
|
| 18 |
-
- embedding-data/flickr30k-captions
|
| 19 |
-
- embedding-data/altlex
|
| 20 |
-
- embedding-data/simple-wiki
|
| 21 |
-
- embedding-data/QQP
|
| 22 |
-
- embedding-data/SPECTER
|
| 23 |
-
- embedding-data/PAQ_pairs
|
| 24 |
-
- embedding-data/WikiAnswers
|
| 25 |
language: en
|
| 26 |
-
library_name: sentence-transformers
|
| 27 |
license: apache-2.0
|
| 28 |
-
|
| 29 |
tags:
|
| 30 |
- sentence-transformers
|
| 31 |
- feature-extraction
|
| 32 |
- sentence-similarity
|
| 33 |
- transformers
|
| 34 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
---
|
| 36 |
|
| 37 |
-
#
|
| 38 |
-
This
|
| 39 |
-
Refer to the [original model card](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) for more details on the model.
|
| 40 |
|
| 41 |
-
## Use with llama.cpp
|
| 42 |
-
Install llama.cpp through brew (works on Mac and Linux)
|
| 43 |
|
| 44 |
-
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
```
|
| 48 |
-
Invoke the llama.cpp server or the CLI.
|
| 49 |
|
| 50 |
-
### CLI:
|
| 51 |
```bash
|
| 52 |
-
|
| 53 |
```
|
| 54 |
|
| 55 |
-
|
| 56 |
-
```
|
| 57 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
```
|
| 59 |
|
| 60 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
git clone https://github.com/ggerganov/llama.cpp
|
| 65 |
-
```
|
| 66 |
|
| 67 |
-
|
| 68 |
-
|
| 69 |
-
|
| 70 |
-
|
|
|
|
|
|
|
| 71 |
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
```
|
| 78 |
-
|
|
|
|
|
|
|
|
|
|
| 79 |
```
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
language: en
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
+
library_name: sentence-transformers
|
| 5 |
tags:
|
| 6 |
- sentence-transformers
|
| 7 |
- feature-extraction
|
| 8 |
- sentence-similarity
|
| 9 |
- transformers
|
| 10 |
+
- drilling-engineering
|
| 11 |
+
datasets:
|
| 12 |
+
- oil-gas-engineering-docs
|
| 13 |
+
- drilling-engineering-manuals
|
| 14 |
+
- well-drilling-reports
|
| 15 |
+
- casing-design-guidelines
|
| 16 |
+
- mud-logging-data
|
| 17 |
+
- managed-pressure-drilling-reports
|
| 18 |
+
- directional-drilling-studies
|
| 19 |
+
pipeline_tag: sentence-similarity
|
| 20 |
---
|
| 21 |
|
| 22 |
+
# OGAI-Embedder
|
| 23 |
+
This is a [sentence-transformers](https://www.SBERT.net) model fine-tuned specifically for **drilling engineering** applications in the oil and gas industry. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for tasks like **technical document retrieval, automated report analysis, and intelligent search** within **drilling-related datasets**.
|
|
|
|
| 24 |
|
|
|
|
|
|
|
| 25 |
|
| 26 |
+
## Usage (Sentence-Transformers)
|
| 27 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
|
|
|
|
|
|
|
|
|
| 28 |
|
|
|
|
| 29 |
```bash
|
| 30 |
+
pip install -U sentence-transformers
|
| 31 |
```
|
| 32 |
|
| 33 |
+
Then you can use the model like this:
|
| 34 |
+
```python
|
| 35 |
+
from sentence_transformers import SentenceTransformer
|
| 36 |
+
sentences = ["What is the optimal mud weight for a high-angle well?", "How does managed pressure drilling improve well control?"]
|
| 37 |
+
|
| 38 |
+
model = SentenceTransformer('OGAI-Embedder')
|
| 39 |
+
embeddings = model.encode(sentences)
|
| 40 |
+
print(embeddings)
|
| 41 |
```
|
| 42 |
|
| 43 |
+
## Drilling-Specific Search and Retrieval
|
| 44 |
+
OGAI-Embedder can be used in **document search engines** for drilling operations, enabling semantic search across:
|
| 45 |
+
- Well drilling reports
|
| 46 |
+
- Casing design manuals
|
| 47 |
+
- Mud logging data
|
| 48 |
+
- Directional drilling surveys
|
| 49 |
+
- Equipment specifications
|
| 50 |
+
- Well control procedures
|
| 51 |
|
| 52 |
+
## Training Data for Drilling Engineering
|
| 53 |
+
The model has been fine-tuned using a **curated dataset** of drilling engineering documents, manuals, and field reports.
|
|
|
|
|
|
|
| 54 |
|
| 55 |
+
### Key Datasets Used:
|
| 56 |
+
| Dataset | Description |
|
| 57 |
+
|---------|------------|
|
| 58 |
+
| Well Drilling Reports | Real-world drilling reports from operators |
|
| 59 |
+
| Casing Design Guidelines | Technical best practices for casing design |
|
| 60 |
+
| Mud Logging Data | Drilling fluid parameters and performance records |
|
| 61 |
|
| 62 |
+
## Deployment for AI-Powered Drilling Engineering Assistance
|
| 63 |
+
OGAI-Embedder is designed for **real-time AI integration** into oil and gas platforms. It enables:
|
| 64 |
+
- **Automated report analysis** for drilling engineers.
|
| 65 |
+
- **Intelligent document retrieval** from large drilling knowledge bases.
|
| 66 |
+
- **Context-aware AI assistants** for well planning and execution.
|
| 67 |
+
- **Enhanced decision-making** based on historical well performance data.
|
| 68 |
+
|
| 69 |
+
## Model Deployment
|
| 70 |
+
This model can be used with `llama.cpp` for efficient inference in drilling engineering applications.
|
| 71 |
+
|
| 72 |
+
```bash
|
| 73 |
+
brew install llama.cpp
|
| 74 |
+
llama-cli --hf-repo OGAI-Embedder --hf-file ogai-embedder-q5_0.gguf -p "What are the key challenges in managed pressure drilling?"
|
| 75 |
```
|
| 76 |
+
|
| 77 |
+
To run a server:
|
| 78 |
+
```bash
|
| 79 |
+
llama-server --hf-repo OGAI-Embedder --hf-file ogai-embedder-q5_0.gguf -c 2048
|
| 80 |
```
|
| 81 |
+
|
| 82 |
+
This model is available on Hugging Face for research and commercial use under the Apache 2.0 license.
|
| 83 |
+
|