Instructions to use ArmanAsq/AYA-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArmanAsq/AYA-8B with Transformers:

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

pipe = pipeline("text-generation", model="ArmanAsq/AYA-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArmanAsq/AYA-8B")
model = AutoModelForCausalLM.from_pretrained("ArmanAsq/AYA-8B")
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

vLLM

How to use ArmanAsq/AYA-8B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ArmanAsq/AYA-8B

SGLang

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

Docker Model Runner
How to use ArmanAsq/AYA-8B with Docker Model Runner:
```
docker model run hf.co/ArmanAsq/AYA-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

AYA-8B

This model is a fine-tuned version of CohereForAI/aya-23-8B on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.0612

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	21	1.8918
No log	2.0	42	1.9454
No log	3.0	63	2.2400
No log	4.0	84	2.4862
No log	5.0	105	2.5904
No log	6.0	126	2.8061
No log	7.0	147	2.8986
No log	8.0	168	2.9773
No log	9.0	189	3.0367
No log	10.0	210	3.0612

Framework versions

Transformers 4.41.2
Pytorch 2.2.1
Datasets 2.19.2
Tokenizers 0.19.1

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

F32

Model tree for ArmanAsq/AYA-8B

Base model

CohereLabs/aya-23-8B

Finetuned

(6)

this model

Quantizations

1 model