AFM-4.5B-Base-KDA-NoPE

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "arcee-ai/AFM-4.5B-Base-KDA-NoPE"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

prompt = "The theory of relativity states that"
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=100,
    do_sample=True,
    temperature=0.7,
    top_p=0.95
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))