Full merged 16bit model of win10/Phi-4-llama-t1-lora, please always thank the original author for all the hardwork!!! All I did is the simple merging work on colab.
Run with Pytorch
import transformers
pipeline = transformers.pipeline(
"text-generation",
model="benhaotang/Phi-4-llama-t1-full",
tokenizer=tokenizer,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a helpful AI asistent. You always think step by step."},
{"role": "user", "content": "Give me a short intodcution to renormalization group(RG) flow in physcis?"},
]
outputs = pipeline(messages, max_new_tokens=128)
print(outputs[0]["generated_text"])
Or can do static GGUF version of quants: benhaotang/Phi-4-llama-t1-full
ollama run hf.co/benhaotang/Phi-4-llama-t1-full-Q4_K_M-GGUF