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

Libraries

How to use SaintsStudios/Mazgu with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("SaintsStudios/Mazgu_Small-T_130M")
model = PeftModel.from_pretrained(base_model, "SaintsStudios/Mazgu")

Transformers

How to use SaintsStudios/Mazgu with Transformers:

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

pipe = pipeline("text-generation", model="SaintsStudios/Mazgu")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SaintsStudios/Mazgu")
model = AutoModelForCausalLM.from_pretrained("SaintsStudios/Mazgu", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SaintsStudios/Mazgu with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SaintsStudios/Mazgu

SGLang

How to use SaintsStudios/Mazgu 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 "SaintsStudios/Mazgu" \
    --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": "SaintsStudios/Mazgu",
		"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 "SaintsStudios/Mazgu" \
        --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": "SaintsStudios/Mazgu",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SaintsStudios/Mazgu with Docker Model Runner:
```
docker model run hf.co/SaintsStudios/Mazgu
```

Mazgu / README.md

Mwanzau

Update README.md

09b2f45 verified 4 days ago

preview code

Raw

History Blame Contribute Delete

746 Bytes

metadata

base_model: SaintsStudios/Mazgu_Small-T_130M
library_name: peft
pipeline_tag: text-generation
tags:
  - base_model:adapter:SaintsStudios/Mazgu_Small-T_130M
  - lora
  - sft
  - transformers
  - trl
language:
  - en
  - ny
  - to
  - ln
  - sw
  - sn
  - tum
  - lin
license: apache-2.0

Mazgu

Mazgu is a bilingual Large Language Model (LLM) developed by Saints Studios, specifically optimized for Tumbuka (Tumbuka) and English.

Model Details

Architecture: Llama-based architecture
Parameters: ~130 Million
Vocabulary Size: 32,000 tokens
Context Length: 512 tokens
Training Data: A curated blend of Tumbuka translated datasets (Gutenberg, TinyStories) and English Light Novels.

Framework versions

PEFT 0.20.0