Sentence Similarity
sentence-transformers
Safetensors
modernbert
feature-extraction
dense
Generated from Trainer
dataset_size:800640
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use Shuu12121/Owl-ph2-len2048 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Shuu12121/Owl-ph2-len2048 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Shuu12121/Owl-ph2-len2048") 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] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,15 @@ library_name: sentence-transformers
|
|
| 14 |
|
| 15 |
# Shuu12121/Owl-ph2-len2048 π¦
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
## Model Details
|
| 18 |
|
| 19 |
### Model Description
|
|
@@ -39,7 +48,7 @@ SentenceTransformer(
|
|
| 39 |
(0): Transformer({'max_seq_length': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
|
| 40 |
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
| 41 |
)
|
| 42 |
-
```
|
| 43 |
|
| 44 |
## Intended Uses
|
| 45 |
|
|
@@ -73,22 +82,50 @@ The training set contains approximately **100,000 samples per language**, result
|
|
| 73 |
* **Epochs:** 1
|
| 74 |
* **Loss:** MultipleNegativesRankingLoss
|
| 75 |
|
|
|
|
|
|
|
| 76 |
## Integrations
|
| 77 |
|
| 78 |
-
### Owl-CLI
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
|
| 80 |
-
|
| 81 |
|
| 82 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
|
| 84 |
-
|
| 85 |
|
| 86 |
-
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
-
|
| 91 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
|
| 93 |
-
|
| 94 |
-
https://github.com/Shun0212/Owl-CLI
|
|
|
|
| 14 |
|
| 15 |
# Shuu12121/Owl-ph2-len2048 π¦
|
| 16 |
|
| 17 |
+
```
|
| 18 |
+
βββββββ βββ ββββββ βββββββ βββ βββ
|
| 19 |
+
ββββββββββββ ββββββ ββββββββ βββ βββ ,______,
|
| 20 |
+
βββ ββββββ ββ ββββββ βββββββ βββ βββ βββ ( O v O )
|
| 21 |
+
βββ ββββββββββββββββ βββββββ βββ βββ βββ / V \
|
| 22 |
+
βββββββββββββββββββββββββββ ββββββββ ββββββββ βββ /( )\
|
| 23 |
+
βββββββ ββββββββ ββββββββ βββββββ ββββββββ βββ ^^ ^^
|
| 24 |
+
```
|
| 25 |
+
|
| 26 |
## Model Details
|
| 27 |
|
| 28 |
### Model Description
|
|
|
|
| 48 |
(0): Transformer({'max_seq_length': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
|
| 49 |
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
| 50 |
)
|
| 51 |
+
```
|
| 52 |
|
| 53 |
## Intended Uses
|
| 54 |
|
|
|
|
| 82 |
* **Epochs:** 1
|
| 83 |
* **Loss:** MultipleNegativesRankingLoss
|
| 84 |
|
| 85 |
+
---
|
| 86 |
+
|
| 87 |
## Integrations
|
| 88 |
|
| 89 |
+
### π¦ Owl-CLI β Semantic Code Search in Your Terminal
|
| 90 |
+
|
| 91 |
+
> **Repository:** [https://github.com/Shun0212/Owl-CLI](https://github.com/Shun0212/Owl-CLI)
|
| 92 |
+
|
| 93 |
+
**Owl-ph2-len2048** is the embedding backbone of **[Owl-CLI](https://github.com/Shun0212/Owl-CLI)**, a command-line tool for semantic code search powered by dense retrieval.
|
| 94 |
+
|
| 95 |
+
Owl-CLI indexes your codebase at the **function level**, encodes each function using this model, and performs **vector similarity search** to find relevant code for natural language queries β directly from your terminal.
|
| 96 |
|
| 97 |
+
#### Key Features
|
| 98 |
|
| 99 |
+
| Feature | Description |
|
| 100 |
+
|---|---|
|
| 101 |
+
| Semantic search | Natural language β relevant functions via dense embeddings |
|
| 102 |
+
| Function-level indexing | Indexed with file paths and line numbers |
|
| 103 |
+
| Differential cache | Only re-embeds changed files |
|
| 104 |
+
| JSON output | Easy integration with other tools and scripts |
|
| 105 |
+
| MCP server support | Plug into AI coding agents (e.g., Claude Code, Cursor) |
|
| 106 |
|
| 107 |
+
#### Example: Query Routing
|
| 108 |
|
| 109 |
+

|
| 110 |
+
|
| 111 |
+
#### Example: Interactive Session
|
| 112 |
+
|
| 113 |
+

|
| 114 |
+
|
| 115 |
+
#### Quick Start
|
| 116 |
+
|
| 117 |
+
```bash
|
| 118 |
+
# Install
|
| 119 |
+
git clone https://github.com/Shun0212/Owl-CLI.git
|
| 120 |
+
|
| 121 |
+
# Index your codebase and search
|
| 122 |
+
owl search "function that handles authentication"
|
| 123 |
+
|
| 124 |
+
# JSON output for tool integration
|
| 125 |
+
owl search "parse config file" --json
|
| 126 |
+
|
| 127 |
+
# Start MCP server for AI agent integration
|
| 128 |
+
owl mcp
|
| 129 |
+
```
|
| 130 |
|
| 131 |
+
For full documentation and installation instructions, see the [Owl-CLI repository](https://github.com/Shun0212/Owl-CLI).
|
|
|