Sentence Similarity
GGUF
sentence-transformers
English
Korean
GGUF
feature-extraction
mteb
korean
retrieval
Instructions to use mykor/comsat-embed-ko-8b-preview-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use mykor/comsat-embed-ko-8b-preview-GGUF with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("mykor/comsat-embed-ko-8b-preview-GGUF") 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
- Local Apps Settings
- llama.cpp
How to use mykor/comsat-embed-ko-8b-preview-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M
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 server with a web UI: ./build/bin/llama-server -hf mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M
Use Docker
docker model run hf.co/mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use mykor/comsat-embed-ko-8b-preview-GGUF with Ollama:
ollama run hf.co/mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M
- Unsloth Studio
How to use mykor/comsat-embed-ko-8b-preview-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for mykor/comsat-embed-ko-8b-preview-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for mykor/comsat-embed-ko-8b-preview-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for mykor/comsat-embed-ko-8b-preview-GGUF to start chatting
- Docker Model Runner
How to use mykor/comsat-embed-ko-8b-preview-GGUF with Docker Model Runner:
docker model run hf.co/mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M
- Lemonade
How to use mykor/comsat-embed-ko-8b-preview-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull mykor/comsat-embed-ko-8b-preview-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.comsat-embed-ko-8b-preview-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
comsat-embed-ko-8b-preview-GGUF
import numpy as np
from llama_cpp import Llama
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim
model = SentenceTransformer(
"sionic-ai/comsat-embed-ko-8b-preview",
)
llama = Llama.from_pretrained(
repo_id="mykor/comsat-embed-ko-8b-preview-GGUF",
filename="comsat-embed-ko-8B-preview-BF16.gguf",
verbose=False,
embedding=True,
n_ctx=0,
)
text = """λ¨μμλ λλ₯Ό λ λ λ ν¬λ―Έν΄μ§κ³
μ΄λ€ μΈλ‘μμ νκ³ μ΄μκ°λλΌλ
λ΄κ² λΏμλ κΈ°μ΅μ λ μ°¬λνκ² λ²μ Έ
μμ§λ λ μ μμ§λ λͺ»νκ³ λ
μ λ λ, λ μ κ°ν κ² κ°μλ°
κ²μ μ§λ¦° μ±λ‘
μ²μμ΄λΌμ κ·Έλ
κ°λ³Έ μ μλ κΈΈμ
λ μ μ μμ μ±
κ°μλ₯Ό μΈμ΄ μ±
μμ² λ κ½μμ²λΌ
λ¨μ΄μ§ λ λ΄ μμ μ‘μμ€λ?
λμ λ°€μ μ§μΈκ²
λΉμΌλ‘ λ
λ΄ λ§μ ν κ·Έλ¦Όμλ λ μΌν€λ λ―νκ³
κΈ°λ€λ¦¬λ νμ΄μ λ μ€μ³ κ°λ― λ λκ³
κ²¨μ° λ§€λ¬λ¦° ν¬λ―Έν λ¬λΉμ λ―Έλλ¬μ Έ
μμ§λ λ λ²μ΄λμ§ λͺ»νκ³ λ
μ λ λ, λ μ 무λμ Έκ°λλ°
μ΄μ© μ€ λͺ¨λ₯΄κ³
μ²μμ΄λΌμ κ·Έλ
κ°λ³Έ μ μλ κΈΈμ
λ μ μ μμ μ±
κ°μλ₯Ό μΈμ΄ μ±
μμ² λ κ½μμ²λΌ
λ¨μ΄μ§λ λ΄ μμ μ‘μμ€λ?
λμ λ°€μ μ§μΈκ²
λΉμΌλ‘
κ·Έλ₯ λ¬μλμ μ λλ¨Έμ
μ΄λμμ§λ νλμ΄
μ°λ¦΄ λ€μ μ°Ύμ μ μκ²
κ²μ λ°€μ΄ λ¬΄μμ§ μλ€κΈ°λ³΄λ¨
ν¬κΈ°ν μ μλ κ² μλ oh
μ΄μ μμΌ λ³΄μ΄λ€
μ΄λ―Έ λ°λ»νλλ°
κ³ κ°λ₯Ό λ¨κ΅¬κ³
λ κ·λ₯Ό λ§κ³
λ΄ κ³μ μ§μΌμ£Όλ
λ λμΉ λ λ ν λ² μ‘μμ€λ
μ½μν κ² μ°¬λν λ―Έμλ₯Ό oh, oh (μ€λ λ°€μ΄) oh
μμΉ¨μΌ κ±°μΌ μ°λ¦° λ"""
embed1 = model.encode(text)
embed2 = np.array(llama.embed(text), dtype=np.float32)
print(cos_sim(embed1, embed2).item())
0.9998719096183777
- Downloads last month
- 99
Hardware compatibility
Log In to add your hardware
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Model tree for mykor/comsat-embed-ko-8b-preview-GGUF
Base model
Qwen/Qwen3-8B-Base Finetuned
Qwen/Qwen3-Embedding-8B Finetuned
sionic-ai/comsat-embed-ko-8b-preview