Model Summary

The language model phi-1.5 is a Transformer with 1.3 billion parameters. It was trained using the same data sources as phi-1, augmented with a new data source that consists of various NLP synthetic texts. When assessed against benchmarks testing common sense, language understanding, and logical reasoning, phi-1.5 demonstrates a nearly state-of-the-art performance among models with less than 10 billion parameters.

We did not fine-tune phi-1.5 either for instruction following or through reinforcement learning from human feedback. The intention behind crafting this open-source model is to provide the research community with a non-restricted small model to explore vital safety challenges, such as reducing toxicity, understanding societal biases, enhancing controllability, and more.

For a safer model release, we exclude generic web-crawl data sources such as common-crawl from the training. This strategy prevents direct exposure to potentially harmful online content, enhancing the model's safety without RLHF. However, the model is still vulnerable to generating harmful content. We hope the model can help the research community to further study the safety of language models.

phi-1.5 can write poems, draft emails, create stories, summarize texts, write Python code (such as downloading a Hugging Face transformer model), etc.

Intended Uses

Given the nature of the training data, phi-1.5 is best suited for prompts using the QA format, the chat format, and the code format. Note that phi-1.5, being a base model, often produces irrelevant text following the main answer. In the following example, we've truncated the answer for illustrative purposes only.

QA format:

Write a detailed analogy between mathematics and a lighthouse.

Answer: Mathematics is like a lighthouse, guiding us through the vast ocean of numbers and calculations. Just as a lighthouse illuminates the darkness, mathematics provides us with a clear path to navigate through complex problems. It helps us make sense of the world around us, just like a lighthouse helps ships find their way home.

where the model generates the text after "Answer:".

Chat format:

Alice: I don't know why, I'm struggling to maintain focus while studying. Any suggestions?

Bob: Have you tried using a timer? It can help you stay on track and avoid distractions.

Alice: That's a good idea. I'll give it a try.

Charlie: Another thing that can help is to break up your study sessions into smaller chunks. It's easier to concentrate on one thing at a time.

Alice: That makes sense. I'll try that too.

Bob: And don't forget to take breaks! It's important to give your brain a rest so you can come back to your studies with a fresh perspective.

Alice: Thanks for the advice, guys. I feel more motivated now.

Charlie: No problem, Alice. We're all in this together.

Bob: Yeah, and remember that it's okay to ask for help if you need it. We're here to support each other.

where the model generates the text after the first "Bob:".

Code format:

def print_prime(n):
   """
   Print all primes between 1 and n
   """
   primes = []
   for num in range(2, n+1):
       is_prime = True
       for i in range(2, int(math.sqrt(num))+1):
           if num % i == 0:
               is_prime = False
               break
       if is_prime:
           primes.append(num)
   print(primes)

where the model generates the text after the comments.

Notes

Limitations of phi-1.5

Training

Model

Software

License

The model is licensed under the Research License.

Sample Code

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

torch.set_default_device("cuda")
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-1_5", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-1_5", trust_remote_code=True)
inputs = tokenizer('''```python
def print_prime(n):
   """
   Print all primes between 1 and n
   """''', return_tensors="pt", return_attention_mask=False)

outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)

If you need to use the model in a lower precision (e.g., FP16), please wrap the model's forward pass with torch.autocast(), as follows:

with torch.autocast(model.device.type, dtype=torch.float16, enabled=True):
    outputs = model.generate(**inputs, max_length=200)

Remark. In the generation function, our model currently does not support beam search (num_beams > 1). Furthermore, in the forward pass of the model, we currently do not support outputting hidden states or attention values, or using custom input embeddings (instead of the model's).

Citation

You can find the paper at https://arxiv.org/abs/2309.05463

@article{textbooks2,
  title={Textbooks Are All You Need II: \textbf{phi-1.5} technical report},
  author={Li, Yuanzhi and Bubeck, S{\'e}bastien and Eldan, Ronen and Del Giorno, Allie and Gunasekar, Suriya and Lee, Yin Tat},
  journal={arXiv preprint arXiv:2309.05463},
  year={2023}
}