Instructions to use CraneAILabs/ganda-gemma-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CraneAILabs/ganda-gemma-1b with Transformers:

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

pipe = pipeline("text-generation", model="CraneAILabs/ganda-gemma-1b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CraneAILabs/ganda-gemma-1b")
model = AutoModelForCausalLM.from_pretrained("CraneAILabs/ganda-gemma-1b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CraneAILabs/ganda-gemma-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CraneAILabs/ganda-gemma-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CraneAILabs/ganda-gemma-1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CraneAILabs/ganda-gemma-1b

SGLang

How to use CraneAILabs/ganda-gemma-1b 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 "CraneAILabs/ganda-gemma-1b" \
    --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": "CraneAILabs/ganda-gemma-1b",
		"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 "CraneAILabs/ganda-gemma-1b" \
        --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": "CraneAILabs/ganda-gemma-1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CraneAILabs/ganda-gemma-1b with Docker Model Runner:
```
docker model run hf.co/CraneAILabs/ganda-gemma-1b
```

Bronsn commited on Aug 3, 2025

Commit

5446a3c

verified ·

1 Parent(s): 84d8582

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -22

README.md CHANGED Viewed

@@ -159,19 +159,6 @@ generation_config = {
 - **Conversational Practice**: Improve Luganda dialogue skills
 - **Text Summarization**: Summarize content in Luganda
-## 💻 System Requirements
-### Minimum Requirements
-- **RAM**: 4GB+ for inference
-- **Storage**: 3GB+ available space
-- **Python**: 3.8+
-- **PyTorch**: 1.9+
-### Recommended Requirements
-- **RAM**: 8GB+ for optimal performance
-- **GPU**: 4GB+ VRAM for faster inference
-- **Storage**: 5GB+ available space
 ## ⚠️ Limitations
 - **Language Output**: Responds only in Luganda
@@ -180,15 +167,6 @@ generation_config = {
 - **Context Length**: Limited to 4,096 tokens for optimal performance
 - **Specialized Domains**: May require domain-specific fine-tuning
-## 🤝 Training Details
-- **Base Model**: Gemma 3 1B Instruction Tuned
-- **Training Method**: GRPO (Generalized Reward Preference Optimization)
-- **Context Length**: 4,096 tokens
-- **Architecture**: Transformer with sliding window attention
-- **Tokenizer**: SentencePiece with 262K vocabulary
-- **Parameters**: 1 billion
 ## 📄 License
 This model is released under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms). Please review the terms before use.

 - **Conversational Practice**: Improve Luganda dialogue skills
 - **Text Summarization**: Summarize content in Luganda
 ## ⚠️ Limitations
 - **Language Output**: Responds only in Luganda
 - **Context Length**: Limited to 4,096 tokens for optimal performance
 - **Specialized Domains**: May require domain-specific fine-tuning
 ## 📄 License
 This model is released under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms). Please review the terms before use.