Instructions to use Snowflake/snowflake-arctic-embed-m-v1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Snowflake/snowflake-arctic-embed-m-v1.5 with sentence-transformers:

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("Snowflake/snowflake-arctic-embed-m-v1.5")

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]

Transformers.js

How to use Snowflake/snowflake-arctic-embed-m-v1.5 with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('sentence-similarity', 'Snowflake/snowflake-arctic-embed-m-v1.5');

llama-cpp-python

How to use Snowflake/snowflake-arctic-embed-m-v1.5 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Snowflake/snowflake-arctic-embed-m-v1.5",
	filename="gguf/snowflake-arctic-embed-m-v1.5-bf16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Snowflake/snowflake-arctic-embed-m-v1.5 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Snowflake/snowflake-arctic-embed-m-v1.5:BF16
# Run inference directly in the terminal:
llama-cli -hf Snowflake/snowflake-arctic-embed-m-v1.5:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Snowflake/snowflake-arctic-embed-m-v1.5:BF16
# Run inference directly in the terminal:
llama-cli -hf Snowflake/snowflake-arctic-embed-m-v1.5: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 Snowflake/snowflake-arctic-embed-m-v1.5:BF16
# Run inference directly in the terminal:
./llama-cli -hf Snowflake/snowflake-arctic-embed-m-v1.5: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 Snowflake/snowflake-arctic-embed-m-v1.5:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Snowflake/snowflake-arctic-embed-m-v1.5:BF16

Use Docker

docker model run hf.co/Snowflake/snowflake-arctic-embed-m-v1.5:BF16

LM Studio
Jan
Ollama
How to use Snowflake/snowflake-arctic-embed-m-v1.5 with Ollama:
```
ollama run hf.co/Snowflake/snowflake-arctic-embed-m-v1.5:BF16
```

Unsloth Studio

How to use Snowflake/snowflake-arctic-embed-m-v1.5 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 Snowflake/snowflake-arctic-embed-m-v1.5 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 Snowflake/snowflake-arctic-embed-m-v1.5 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Snowflake/snowflake-arctic-embed-m-v1.5 to start chatting

Docker Model Runner
How to use Snowflake/snowflake-arctic-embed-m-v1.5 with Docker Model Runner:
```
docker model run hf.co/Snowflake/snowflake-arctic-embed-m-v1.5:BF16
```

Lemonade

How to use Snowflake/snowflake-arctic-embed-m-v1.5 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Snowflake/snowflake-arctic-embed-m-v1.5:BF16

Run and chat with the model

lemonade run user.snowflake-arctic-embed-m-v1.5-BF16

List all available models

lemonade list

noooop commited on Apr 17, 2025

Commit

ef5ae09

verified ·

1 Parent(s): 8e4eaca

Use is_matryoshka to denote whether a model is compatible with Matryoshka Representation Learning (MRL).

Browse files

I come from the vllm community, and recently vllm has added [support for Matryoshka Representation Learning (MRL)](https://github.com/vllm-project/vllm/pull/16331).

Not all embeddings models support MRL. Changing the output dimension for models that do not support MRL will lead to poor results.

We hope that the open source community will adopt the terms “is_matryoshka ” or “matryoshka_dimensions ” to denote whether a model is compatible with Matryoshka Representation Learning (MRL).

Files changed (1) hide show

config.json +1 -0

config.json CHANGED Viewed

@@ -22,5 +22,6 @@
   "transformers_version": "4.39.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522
 }

   "transformers_version": "4.39.3",
   "type_vocab_size": 2,
   "use_cache": true,
+  "is_matryoshka": true,
   "vocab_size": 30522
 }