Instructions to use cortexso/deepscaler with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cortexso/deepscaler with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/deepscaler",
	filename="deepscaler-1.5b-preview-q2_k.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cortexso/deepscaler with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/deepscaler:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/deepscaler:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/deepscaler:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/deepscaler: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 cortexso/deepscaler:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cortexso/deepscaler: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 cortexso/deepscaler:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/deepscaler:Q4_K_M

Use Docker

docker model run hf.co/cortexso/deepscaler:Q4_K_M

LM Studio
Jan

vLLM

How to use cortexso/deepscaler with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/deepscaler"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cortexso/deepscaler",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cortexso/deepscaler:Q4_K_M

Ollama
How to use cortexso/deepscaler with Ollama:
```
ollama run hf.co/cortexso/deepscaler:Q4_K_M
```

Unsloth Studio new

How to use cortexso/deepscaler 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 cortexso/deepscaler 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 cortexso/deepscaler to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cortexso/deepscaler to start chatting

Docker Model Runner
How to use cortexso/deepscaler with Docker Model Runner:
```
docker model run hf.co/cortexso/deepscaler:Q4_K_M
```

Lemonade

How to use cortexso/deepscaler with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/deepscaler:Q4_K_M

Run and chat with the model

lemonade run user.deepscaler-Q4_K_M

List all available models

lemonade list

Overview

Deepscaler is an advanced AI model developed from the agentica-org's DeepScaleR-1.5B-Preview, designed to enhance the efficiency and scalability of various machine learning tasks. Its core purpose is to provide high-quality predictive analytics and data processing capabilities while optimizing resource usage. Deepscaler is particularly useful in scenarios such as natural language processing, computer vision, and more complex data interpretation tasks, making it suitable for applications in industries like finance, healthcare, and entertainment. Users can leverage its performance to achieve faster training times and improved accuracy in their models. Overall, Deepscaler's architecture allows it to deliver robust results with reduced computational overhead, making it an excellent choice for developers and organizations aiming to scale their AI solutions.

Variants

No	Variant	Cortex CLI command
1	Deepscaler-1.5b	cortex run deepscaler:1.5b

Use it with Jan (UI)

Install Jan using Quickstart
Use in Jan model Hub:
```
cortexso/deepscaler
```

Use it with Cortex (CLI)

Install Cortex using Quickstart
Run the model with command:
```
cortex run deepscaler
```

Credits

Author: agentica-org
Converter: Homebrew
Original License: LICENSE

Downloads last month: 130

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit