Instructions to use Jaward/afri-aya-vision-krio-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jaward/afri-aya-vision-krio-8b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("CohereLabs/aya-vision-8b")
model = PeftModel.from_pretrained(base_model, "Jaward/afri-aya-vision-krio-8b")

Transformers

How to use Jaward/afri-aya-vision-krio-8b with Transformers:

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

pipe = pipeline("text-generation", model="Jaward/afri-aya-vision-krio-8b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Jaward/afri-aya-vision-krio-8b")
model = AutoModelForMultimodalLM.from_pretrained("Jaward/afri-aya-vision-krio-8b", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jaward/afri-aya-vision-krio-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jaward/afri-aya-vision-krio-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jaward/afri-aya-vision-krio-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jaward/afri-aya-vision-krio-8b

SGLang

How to use Jaward/afri-aya-vision-krio-8b 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 "Jaward/afri-aya-vision-krio-8b" \
    --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": "Jaward/afri-aya-vision-krio-8b",
		"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 "Jaward/afri-aya-vision-krio-8b" \
        --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": "Jaward/afri-aya-vision-krio-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Jaward/afri-aya-vision-krio-8b 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 Jaward/afri-aya-vision-krio-8b 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 Jaward/afri-aya-vision-krio-8b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Jaward/afri-aya-vision-krio-8b to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Jaward/afri-aya-vision-krio-8b",
    max_seq_length=2048,
)

Docker Model Runner
How to use Jaward/afri-aya-vision-krio-8b with Docker Model Runner:
```
docker model run hf.co/Jaward/afri-aya-vision-krio-8b
```

afri-aya-vision-krio-8b / config.json

Jaward

(Trained with Unsloth)

edaeb56 verified 10 months ago

Raw

History Blame Contribute Delete

2.87 kB

	{
	"adapter_layer_norm_eps": 1e-06,
	"alignment_activation_fn": "swiglu",
	"alignment_intermediate_size": 28672,
	"architectures": [
	"AyaVisionForConditionalGeneration"
	],
	"downsample_factor": 2,
	"image_token_index": 255036,
	"max_splits_per_img": 12,
	"model_type": "aya_vision",
	"pad_token_id": 0,
	"projector_hidden_act": "gelu",
	"text_config": {
	"_sliding_window_pattern": 4,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"layer_norm_eps": 1e-05,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"logit_scale": 0.25,
	"max_position_embeddings": 8192,
	"model_max_length": 16384,
	"model_type": "cohere2",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 8,
	"rope_scaling": null,
	"rope_theta": 50000,
	"sliding_window": 4096,
	"torch_dtype": "bfloat16",
	"use_cache": true,
	"use_qk_norm": false,
	"vocab_size": 256000
	},
	"torch_dtype": "bfloat16",
	"transformers_version": "4.55.4",
	"unsloth_version": "2025.9.11",
	"vision_config": {
	"attention_dropout": 0.0,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"image_size": 364,
	"intermediate_size": 4304,
	"layer_norm_eps": 1e-06,
	"model_type": "siglip_vision_model",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 27,
	"patch_size": 14,
	"torch_dtype": "bfloat16",
	"vision_use_head": false
	},
	"vision_feature_layer": -1,
	"vision_feature_select_strategy": "full"
	}