Sentence Similarity
GGUF
English
Chinese
multilingual
feature-extraction
embedding
text-embedding
retrieval
Instructions to use mykor/Octen-Embedding-0.6B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use mykor/Octen-Embedding-0.6B-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible embeddings server: llama serve -hf mykor/Octen-Embedding-0.6B-GGUF:Q4_K_M --embeddings
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible embeddings server: llama serve -hf mykor/Octen-Embedding-0.6B-GGUF:Q4_K_M --embeddings
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible embeddings server: ./llama-server -hf mykor/Octen-Embedding-0.6B-GGUF:Q4_K_M --embeddings
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible embeddings server: ./build/bin/llama-server -hf mykor/Octen-Embedding-0.6B-GGUF:Q4_K_M --embeddings
- Llama new
- LM Studio
- Jan
- Ollama
How to use mykor/Octen-Embedding-0.6B-GGUF with Ollama:
ollama run hf.co/mykor/Octen-Embedding-0.6B-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use mykor/Octen-Embedding-0.6B-GGUF with Docker Model Runner:
docker model run hf.co/mykor/Octen-Embedding-0.6B-GGUF:Q4_K_M
- Lemonade
How to use mykor/Octen-Embedding-0.6B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull mykor/Octen-Embedding-0.6B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Octen-Embedding-0.6B-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Octen-Embedding-0.6B-GGUF
import numpy as np
import torch
from llama_cpp import Llama
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
model = SentenceTransformer(
"Octen/Octen-Embedding-0.6B",
model_kwargs={"dtype": torch.bfloat16},
)
llama = Llama.from_pretrained(
repo_id="mykor/Octen-Embedding-0.6B-GGUF",
filename="Octen-Embedding-0.6B-BF16.gguf",
verbose=False,
embedding=True,
n_ctx=0,
)
text = """์ฒ์์ ๋ฏธ์ฝํ ๋ฌผ๊ฒฐ์ด๊ฒ ์ง๋ง
๊ทธ๋ ๊ฒ ๋์ ๊ฟ์ ๋ฟ์ ์ ์๊ฒ ์ง
๊ฑฐ๋ํ ๋ฐ๋ค์ ๊ฐํ๋ฒ๋ฆฐ ๋๋ฅผ ๊ตฌํ ๋ฐฉ๋ฒ์ ์๊ณ ์์ด
์ ๋๋ก ๋ฉ์ถ์ง ๋ง, ๋น๋๊ณ ์์ผ๋
์, ์ ์ด ๋ณธ๋ค๋ฉด, ์, ํ์น๊ณ ๋ง๊ฑธ
๋ฏฟ์ง ์๋ ๊ฒ๋ค์ ๋ฌด์ํด
์ปค๋ค๋ ํ๋์ ์ผ์ผํค๋
๊ทธ ํ์ ๋๋ ๊ฐ์ง๊ณ ์์ด, ๋ด๊ฒ ๋ณด์ฌ์ค๋
ํ๋์ ์ผ์ผ์ผ ๋๋ถ์ ๋ ๋ณด์ฌ์ค
์ด ๋ฐ๋ค๋ฅผ ์ง์ด์ผํค์
ํ๋์ ์์ ํ๋์ด ์๋์ผ, ๋ฌผ๋ค์ด์ ์๋ก์
์์ผ๋ก ๋น๋๋ ๋ฐ๋ค๋ฅผ (๋ฐ๋ค๋ฅผ) ๋ง๋ค์ด ๊ฐ๋ณด์
์ฟ, ์กฐ์ฉํ ์ด๊ณณ์ ๋๊ตฐ๊ฐ ์์ด
ํ๋์ ํด๋ ํ๋ด๊ณ ์์ด
๋์น์ฑ๋ค๋ฉด, ์ผ๋ฅธ ํค์์ณ
ํด๋ฅผ ์ผํฌ ํฐ ๋ฌผ๊ฒฐ์ ๋ง๋ค์
ํ๋๋ ๋น์ ๊ฐ์ง ๋๋ง์
๋ ์์ฌํ๊ฒ ๋ ํ
์ง๋ง ๋ฏฟ์ด
๊ฐ๋ฅ์ฑ ๊ทธ๊ฑฐ๋ฉด ๋ผ
์ ์ผํ ์์ ๊ฐ์ง๊ณ ์์ผ๋
์, ์ ์ด ์์๋, ์, ๊ฐ์ง ์ ์์ด
๋ฏฟ์ง ์๋ ๊ฒ ๋ค์ ๋ฌด์ํด
์ปค๋ค๋ ํ๋์ ์ผ์ผํค๋
๊ทธ ํ์ ๋๋ ๊ฐ์ง๊ณ ์์ด, ๋ด๊ฒ ๋ณด์ฌ์ค๋
ํ๋์ ์ผ์ผ์ผ ๋๋ถ์ ๋ ๋ณด์ฌ์ค
์ด ๋ฐ๋ค๋ฅผ ์ง์ด์ผํค์
ํ๋์ ์์ ํ๋์ด ์๋์ผ, ๋ฌผ๋ค์ด์ ์๋ก์
์์ผ๋ก ๋น๋๋ ๋ฐ๋ค๋ฅผ (๋ฐ๋ค๋ฅผ) ๋ง๋ค์ด ๊ฐ๋ณด์
๋ ์ ๋ง๋ก ์ด๋ฆฌ์๊ตฌ๋ ๋ด ํ์ ๋ ๋
๋ ์ปค๋ค๋ ๋ฏธ๋๋ฅผ ๊ฟ๊ฟ ์ ์๋ค๊ณ ๋ฏฟ๋ ๋๊ฐ, ๊ทธ๋?
ํ๋์ ์ผ์ผ์ผ ์ฌ์ฐ์ ๊นจ๊ณ ๋์
์ด ๋ฐ๋ค๋ฅผ ์ง์ด์ผํค์
ํ๋์ ์์ ํ๋์ด ์๋์ผ, ๋ฌผ๋ค์ด์ ์ฐ๋ฆฌ์
์์ผ๋ก ๋น๋๋ ๋ฐ๋ค๋ฅผ (๋ฐ๋ค๋ฅผ) ๋ณด์ฌ์ฃผ๋ฌ ๊ฐ์"""
embed1 = model.encode(text)
embed2 = np.array(llama.embed(text), dtype=np.float32)
print(cos_sim(embed1, embed2).item())
0.9998425245285034
- Downloads last month
- 92
Hardware compatibility
Log In to add your hardware
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Model tree for mykor/Octen-Embedding-0.6B-GGUF
Base model
Qwen/Qwen3-0.6B-Base Finetuned
Qwen/Qwen3-Embedding-0.6B Finetuned
Octen/Octen-Embedding-0.6B