Views
No views yet
1 @misc{ultrachat,
2 title={UltraChat: A Large-Scale Auto-generated Multi-round Dialogue Dataset},
3 author={Ding et al.},
4 year={2023},
5 howpublished={\url{https://github.com/thunlp/UltraChat}}
6 }1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained(
4 "Irfanuruchi/phi-2-chat",
5 trust_remote_code=True,
6 device_map="auto"
7)
8tokenizer = AutoTokenizer.from_pretrained("Irfanuruchi/phi-2-chat")
9
10# Recommended prompt format:
11input_text = "<|user|>Explain dark matter<|assistant|>"
12inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
13outputs = model.generate(**inputs, max_new_tokens=200)
14print(tokenizer.decode(outputs[0], skip_special_tokens=True))
151@misc{phi-2-chat,
2 author = {Irfan Uruchi},
3 title = {phi-2-chat: Fine-tuned Phi-2 for conversational AI},
4 year = {2025},
5 publisher = {Hugging Face},
6 howpublished = {\url{https://huggingface.co/Irfanuruchi/phi-2-chat}}
7}
8
9@misc{phi2,
10 title={Phi-2: The Surprisingly Capable Small Language Model},
11 author={Microsoft},
12 year={2023},
13 url={https://www.microsoft.com/en-us/research/blog/phi-2-the-surprising-power-of-small-language-models/}
14}