Shuu12121/Owl-ph2-len2048 🦉

 ██████╗ ██╗    ██╗██╗                ██████╗ ██╗      ██╗
██╔═══██╗██║    ██║██║               ██╔════╝ ██║      ██║      ,______,
██║   ██║██║ █╗ ██║██║      ██████╗  ██║      ██║      ██║     ( O v O )
██║   ██║██║███╗██║██║      ╚═════╝  ██║      ██║      ██║      /  V  \
╚██████╔╝╚███╔███╔╝███████╗          ╚██████╗ ███████╗ ██║     /(     )\
 ╚═════╝  ╚══╝╚══╝ ╚══════╝           ╚═════╝ ╚══════╝ ╚═╝      ^^   ^^

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: Shuu12121/Owl-ph2-base-len2048
• Maximum Sequence Length: 1024 tokens (2048 tokens during pretraining)
• Output Dimensionality: 768
• Similarity Function: Cosine Similarity

This model is a SentenceTransformer variant of Shuu12121/Owl-ph2-base-len2048. It was trained on the Owl corpus for code search and code-text retrieval. The training data consists of roughly 100,000 samples per language (800,640 pairs in total), and the model was trained for 1 epoch with a learning rate of 1e-5.

Model Sources

• Base model: Shuu12121/Owl-ph2-base-len2048
• Sentence Transformers: Sentence Transformers Documentation

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 1024, 'do_lower_case': False, 'architecture': 'ModernBertModel'})
  (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})
)

Intended Uses

This model is intended for:

• code search
• code-text retrieval
• semantic similarity
• dense embedding generation for source code and natural language

Usage

Direct Usage (Sentence Transformers)

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("Shuu12121/Owl-ph2-len2048")

Training Details

Training Dataset

This model was trained on the Owl corpus, a dataset constructed for code search and code-text retrieval. The training set contains approximately 100,000 samples per language, resulting in 800,640 training pairs in total.

Training Hyperparameters

• Learning rate: 1e-5
• Epochs: 1
• Loss: MultipleNegativesRankingLoss

---

Integrations

🦉 Owl-CLI — Semantic Code Search in Your Terminal

Repository: https://github.com/Shun0212/Owl-CLI

Owl-ph2-len2048 is the embedding backbone of Owl-CLI, a command-line tool for semantic code search powered by dense retrieval.

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 — directly from your terminal.

Key Features

Feature	Description
Semantic search	Natural language → relevant functions via dense embeddings
Function-level indexing	Indexed with file paths and line numbers
Differential cache	Only re-embeds changed files
JSON output	Easy integration with other tools and scripts
MCP server support	Plug into AI coding agents (e.g., Claude Code, Cursor)

Example: Query Routing

Example: Interactive Session

Quick Start

# Install
git clone https://github.com/Shun0212/Owl-CLI.git

# Index your codebase and search
owl search "function that handles authentication"

# JSON output for tool integration
owl search "parse config file" --json

# Start MCP server for AI agent integration
owl mcp

For full documentation and installation instructions, see the Owl-CLI repository.