from transformers import pipeline
model_id = "tiny-random/phi-4"
pipe = pipeline(
    "text-generation", model=model_id, device="cuda",
    trust_remote_code=True, max_new_tokens=20,
)
print(pipe("Hello World!"))

Codes to create this repo:

python

import torch

from transformers import (
    AutoConfig,
    AutoModelForCausalLM,
    AutoTokenizer,
    GenerationConfig,
    pipeline,
    set_seed,
)

source_model_id = "microsoft/phi-4"
save_folder = "/tmp/tiny-random/phi-4"

tokenizer = AutoTokenizer.from_pretrained(
    source_model_id, trust_remote_code=True,
)
tokenizer.save_pretrained(save_folder)

config = AutoConfig.from_pretrained(
    source_model_id, trust_remote_code=True,
)
config.hidden_size = 16
config.intermediate_size = 32
config.num_attention_heads = 2
config.num_hidden_layers = 2
config.num_key_value_heads = 1
model = AutoModelForCausalLM.from_config(
    config,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
)
model.generation_config = GenerationConfig.from_pretrained(
    source_model_id, trust_remote_code=True,
)
set_seed(42)
with torch.no_grad():
    for name, p in sorted(model.named_parameters()):
        torch.nn.init.normal_(p, 0, 0.5)
        print(name, p.shape)
model.save_pretrained(save_folder)