Instructions to use adzcai/AfriGuardPlain-tiny-aya-global-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adzcai/AfriGuardPlain-tiny-aya-global-full with Transformers:

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

pipe = pipeline("text-generation", model="adzcai/AfriGuardPlain-tiny-aya-global-full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adzcai/AfriGuardPlain-tiny-aya-global-full")
model = AutoModelForCausalLM.from_pretrained("adzcai/AfriGuardPlain-tiny-aya-global-full", 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 adzcai/AfriGuardPlain-tiny-aya-global-full with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/adzcai/AfriGuardPlain-tiny-aya-global-full

SGLang

How to use adzcai/AfriGuardPlain-tiny-aya-global-full 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 "adzcai/AfriGuardPlain-tiny-aya-global-full" \
    --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": "adzcai/AfriGuardPlain-tiny-aya-global-full",
		"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 "adzcai/AfriGuardPlain-tiny-aya-global-full" \
        --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": "adzcai/AfriGuardPlain-tiny-aya-global-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adzcai/AfriGuardPlain-tiny-aya-global-full with Docker Model Runner:
```
docker model run hf.co/adzcai/AfriGuardPlain-tiny-aya-global-full
```

AfriGuardPlain-tiny-aya-global-full

CohereLabs/tiny-aya-global fine-tuned with full fine-tuning (DeepSpeed ZeRO-3) on adzcai/AfriGuard-plain: the non-instruction-prompted version of israel/AfriGuard-inst.

Each training example is only the user prompt and a plain reply (a helpful answer for safe prompts, a brief refusal for unsafe ones), with no safety system instruction and no <safety> / <category> / <response> tags. The model therefore answers or refuses directly, without emitting a safety label. Its instruction-prompted counterpart (same base model and hyperparameters, trained on AfriGuard-inst) is israel/AfriGuard-tiny-aya-global-full.

Training config: examples/train_full/afriguard_plain_tiny-aya-global_full_sft.yaml in the AfriGuard-model (LlamaFactory) repo; 1 epoch, 1 GPU, chat template of the base model, loss on the response only.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 1.0