LFM2-8B-A1B

pip install transformers

git clone https://github.com/vllm-project/vllm.git
cd vllm
pip install -e . -v

from vllm import LLM, SamplingParams

prompts = [
    [
        {
            "content": "What is C. elegans?",
            "role": "user",
        },
    ],
    [
        {
            "content": "Say hi in JSON format",
            "role": "user",
        },
    ],
    [
        {
            "content": "Define AI in Spanish",
            "role": "user",
        },
    ],
]

sampling_params = SamplingParams(
    temperature=0.3,
    min_p=0.15,
    repetition_penalty=1.05,
    max_tokens=30
)

llm = LLM(model="LiquidAI/LFM2-8B-A1B", dtype="bfloat16")

outputs = llm.chat(prompts, sampling_params)

for i, output in enumerate(outputs):
    prompt = prompts[i][0]["content"]
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")