Instructions to use Danna8/aya-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Danna8/aya-8b with Transformers:

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

pipe = pipeline("text-generation", model="Danna8/aya-8b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Danna8/aya-8b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Danna8/aya-8b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Danna8/aya-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Danna8/aya-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": "Danna8/aya-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Danna8/aya-8b

SGLang

How to use Danna8/aya-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 "Danna8/aya-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": "Danna8/aya-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 "Danna8/aya-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": "Danna8/aya-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Danna8/aya-8b with Docker Model Runner:
```
docker model run hf.co/Danna8/aya-8b
```

Danna8 commited on Mar 14, 2025

Commit

a6157d6

verified ·

1 Parent(s): 07b2e55

Update README.md

Browse files

Files changed (1) hide show

README.md +45 -9

README.md CHANGED Viewed

@@ -1,9 +1,45 @@
-# Aya 8B Model
-This is the Aya 8B model, a multilingual model by Cohere that supports 23 languages.
-This model was uploaded directly from Ollama's Aya model files.
-## Model Structure
-- `/blobs`: Contains the model weight files
-- `/manifests`: Contains the model manifests

+---
+language: en
+tags:
+- text-generation
+- ollama
+- aya
+- llm
+- conversational
+pipeline_tag: text-generation
+library_name: transformers
+inference: true
+---
+# Aya-8B
+## Model Description
+This is the Aya-8B model, originally designed for Ollama and converted to be compatible with Hugging Face. Aya is an open-source language model known for its conversational abilities and text generation capabilities.
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained("Danna8/aya-8b")
+model = AutoModelForCausalLM.from_pretrained("Danna8/aya-8b")
+inputs = tokenizer("Hello, how are you today?", return_tensors="pt")
+outputs = model.generate(inputs["input_ids"], max_length=100)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+```
+## Model Details
+- **Model Type:** Transformer-based language model
+- **Size:** 8 billion parameters
+## Limitations and Biases
+Like all language models, Aya-8B may reproduce biases present in its training data. Users should be aware of these limitations when deploying the model.
+## License