---
datasets:
- NovaSky-AI/Sky-T1_data_17k
base_model:
- win10/Phi-4-llama-t1-lora
license: mit
---

Full merged 16bit model of [win10/Phi-4-llama-t1-lora](https://huggingface.co/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

```python
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](https://huggingface.co/benhaotang/Phi-4-llama-t1-full-Q4_K_M-GGUF)

```
ollama run hf.co/benhaotang/Phi-4-llama-t1-full-Q4_K_M-GGUF
```