   ovms --pull --source_model wizardoftrap/Llama-3.2-1B-Indian-history-openvino --model_repository_path /OpenVinoSP/models --model_name Llama-3.2-1B-Indian-history-openvino --target_device GPU --task text_generation

- Start server:

   ovms --model_path models/wizardoftrap/Llama-3.2-1B-Indian-history-openvino --model_name Llama-3.2-1B-Indian-history-openvino --port 9000 --rest_port 8000 --log_level DEBUG

Usage

python

from openai import OpenAI

client = OpenAI(
    api_key="not-needed",  # OVMS doesn't require API key
    base_url="http://localhost:8000/v3"  # REST endpoint on port 8000
)

MODEL_NAME = "Llama-3.2-1B-Indian-history-openvino"

response = client.chat.completions.create(
            model=MODEL_NAME,
            messages=[
                {"role": "system", "content": SYSTEM_PROMPT},
                {"role": "user", "content": "Hey tell me about Jaliawala bagh"}
            ],
            temperature=0.7,
            max_tokens=512,
            top_p=0.9
        )
print(response.choices[0].message.content)