Instructions to use xJoePec/galena-2b-math-physics with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xJoePec/galena-2b-math-physics with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="xJoePec/galena-2b-math-physics")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("xJoePec/galena-2b-math-physics", dtype="auto")

llama-cpp-python

How to use xJoePec/galena-2b-math-physics with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="xJoePec/galena-2b-math-physics",
	filename="gguf/granite-math-physics-f16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use xJoePec/galena-2b-math-physics with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf xJoePec/galena-2b-math-physics:F16
# Run inference directly in the terminal:
llama-cli -hf xJoePec/galena-2b-math-physics:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf xJoePec/galena-2b-math-physics:F16
# Run inference directly in the terminal:
llama-cli -hf xJoePec/galena-2b-math-physics:F16

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 xJoePec/galena-2b-math-physics:F16
# Run inference directly in the terminal:
./llama-cli -hf xJoePec/galena-2b-math-physics:F16

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 xJoePec/galena-2b-math-physics:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf xJoePec/galena-2b-math-physics:F16

Use Docker

docker model run hf.co/xJoePec/galena-2b-math-physics:F16

LM Studio
Jan

vLLM

How to use xJoePec/galena-2b-math-physics with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xJoePec/galena-2b-math-physics"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xJoePec/galena-2b-math-physics",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xJoePec/galena-2b-math-physics:F16

SGLang

How to use xJoePec/galena-2b-math-physics with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "xJoePec/galena-2b-math-physics" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xJoePec/galena-2b-math-physics",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "xJoePec/galena-2b-math-physics" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xJoePec/galena-2b-math-physics",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use xJoePec/galena-2b-math-physics with Ollama:
```
ollama run hf.co/xJoePec/galena-2b-math-physics:F16
```

Unsloth Studio

How to use xJoePec/galena-2b-math-physics 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 xJoePec/galena-2b-math-physics 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 xJoePec/galena-2b-math-physics to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for xJoePec/galena-2b-math-physics to start chatting

How to use xJoePec/galena-2b-math-physics with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf xJoePec/galena-2b-math-physics:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "xJoePec/galena-2b-math-physics:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use xJoePec/galena-2b-math-physics with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf xJoePec/galena-2b-math-physics:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default xJoePec/galena-2b-math-physics:F16

Run Hermes

hermes

Docker Model Runner
How to use xJoePec/galena-2b-math-physics with Docker Model Runner:
```
docker model run hf.co/xJoePec/galena-2b-math-physics:F16
```

Lemonade

How to use xJoePec/galena-2b-math-physics with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull xJoePec/galena-2b-math-physics:F16

Run and chat with the model

lemonade run user.galena-2b-math-physics-F16

List all available models

lemonade list

xJoePec commited on Nov 18, 2025

Commit

5385d58

verified ·

1 Parent(s): ee1bdb7

Upload CITATION.cff

Browse files

Files changed (1) hide show

CITATION.cff +41 -0

CITATION.cff ADDED Viewed

	@@ -0,0 +1,41 @@

+cff-version: 1.2.0
+message: "If you use this model, please cite it as below."
+type: software
+title: "Galena-2B: Granite 3.3 Math & Physics Model"
+abstract: "A specialized 2-billion parameter language model fine-tuned on advanced mathematics and physics datasets, derived from IBM Granite 3.3-2B Instruct."
+authors:
+  - family-names: "Your Last Name"
+    given-names: "Your First Name"
+    email: your.email@example.com
+    orcid: "https://orcid.org/0000-0000-0000-0000"
+version: 1.0.0
+date-released: 2024-11-17
+license: Apache-2.0
+repository-code: "https://github.com/yourusername/galena-2B"
+keywords:
+  - machine-learning
+  - natural-language-processing
+  - language-model
+  - mathematics
+  - physics
+  - granite
+  - fine-tuning
+  - lora
+  - education
+references:
+  - type: software
+    title: "Granite 3.3: IBM's Open Foundation Models"
+    authors:
+      - name: "IBM Research"
+    year: 2024
+    url: "https://www.ibm.com/granite"
+  - type: dataset
+    title: "Nemotron-RL-Math: Advanced Calculations Dataset"
+    authors:
+      - name: "NVIDIA"
+    url: "https://huggingface.co/datasets/nvidia/Nemotron-RL-math-advanced_calculations"
+  - type: dataset
+    title: "CAMEL Physics Dataset"
+    authors:
+      - name: "CAMEL-AI"
+    url: "https://huggingface.co/datasets/camel-ai/physics"