Instructions to use HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF")

sentences = [
    "那是 個快樂的人",
    "那是 條快樂的狗",
    "那是 個非常幸福的人",
    "今天是晴天"
]
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 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-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 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16

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 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16

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 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16

Use Docker

docker model run hf.co/HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16

LM Studio
Jan
Ollama
How to use HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF with Ollama:
```
ollama run hf.co/HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16
```

Unsloth Studio

How to use HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-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 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-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 HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF to start chatting

Docker Model Runner
How to use HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16
```

Lemonade

How to use HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF:BF16

Run and chat with the model

lemonade run user.KaLM-embedding-multilingual-mini-instruct-v1-GGUF-BF16

List all available models

lemonade list

Atomic Chat

Using llama.cpp for GGUF conversion.

Original model: HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1

Run them directly with llama.cpp:

./llama-embedding \
  --batch-size 512 \
  --ctx-size 512 \
  -m KaLM-embedding-multilingual-mini-instruct-v1-GGUF/model.f32.gguf \
  --pooling mean \
  -p "this is a test sentence for llama cpp"

It is important to note that this model uses the mean pooling method, so the --pooling parameter needs to be specified as mean when invoking it.

Our tests on LM Studio have not yet been successful, and it is unclear whether this is related to the default pooling method used by LM Studio.

If any developers are familiar with how to specify the pooling method for embedding models in LM Studio, we welcome you to contact us for further discussion via the email: yanshek.woo@gmail.com

Downloads last month: 16

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

1-bit

2-bit

8-bit

16-bit

32-bit

Model tree for HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF

Base model

HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1

Quantized

(1)

this model

Collection including HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1-GGUF

Lychee-KaLM-embedding

Collection

16 items • Updated 14 days ago • 25