Phi 3 Small 128k Instruct

🚀 Phi-3-Small-128K-Instruct

Phi-3-Small-128K-Instruct is a lightweight, state-of-the-art open model with 7B parameters. It shows excellent performance in various benchmarks and is suitable for multiple scenarios with specific constraints.

🚀 Quick Start

Phi-3-Small-128K-Instruct has been integrated in the development version (4.40.2) of transformers. Until the official version is released through pip, ensure that you are doing one of the following:

• Install tiktoken (0.6.0) ans triton (2.3.0)

• When loading the model, ensure that trust_remote_code=True is passed as an argument of the from_pretrained() function.

• Update your local transformers to the development version: pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers. The previous command is an alternative to cloning and installing from the source.

The current transformers version can be verified with: pip list | grep transformers.

Phi-3-Small-128K-Instruct is also available in Azure AI.

✨ Features

• Lightweight and High - performance: With 7B parameters, it performs well in benchmarks testing common sense, language understanding, math, code, long context, and logical reasoning among models of the same - size and next - size - up.
• Multiple Context Length Variants: Available in 8K and 128K context length variants, suitable for different application scenarios.
• Designed for Specific Scenarios: Ideal for memory/compute constrained environments, latency bound scenarios, and scenarios requiring strong reasoning (especially code, math, and logic).

📦 Installation

Phi-3-Small-128K-Instruct has been integrated in the development version (4.40.2) of transformers. Before the official pip release, you can:

1. Install tiktoken (0.6.0) and triton (2.3.0).
2. When loading the model, pass trust_remote_code=True as an argument of the from_pretrained() function.
3. Update your local transformers to the development version: pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers.

💻 Usage Examples

Basic Usage

This code snippets show how to get quickly started with running the model on a GPU:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

torch.random.manual_seed(0)
model_id = "microsoft/Phi-3-small-128k-instruct"
model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    torch_dtype="auto", 
    trust_remote_code=True, 
)
assert torch.cuda.is_available(), "This model needs a GPU to run ..."
device = torch.cuda.current_device()
model = model.to(device)
tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    device=device
)

generation_args = {
    "max_new_tokens": 500,
    "return_full_text": False,
    "temperature": 0.0,
    "do_sample": False,
}

output = pipe(messages, **generation_args)
print(output[0]['generated_text'])

Advanced Usage

Some applications/frameworks might not include a BOS token (<|endoftext|>) at the start of the conversation. Please ensure that it is included since it provides more reliable results.

📚 Documentation

Model Summary

The Phi-3-Small-128K-Instruct is a 7B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Phi-3 family with the Small version in two variants 8K and 128K which is the context length (in tokens) that it can support.

The model has underwent a post-training process that incorporates both supervised fine-tuning and direct preference optimization for the instruction following and safety measures. When assessed against benchmarks testing common sense, language understanding, math, code, long context and logical reasoning, Phi-3-Small-128K-Instruct showcased a robust and state-of-the-art performance among models of the same-size and next-size-up.

Resources and Technical Documentation:

• Phi-3 Microsoft Blog
• Phi-3 Technical Report
• Phi-3 on Azure AI Studio
• Phi-3 Cookbook

Intended Uses

Primary use cases

The model is intended for broad commercial and research use in English. The model provides uses for general purpose AI systems and applications which require :

1. Memory/compute constrained environments
2. Latency bound scenarios
3. Strong reasoning (especially code, math and logic)

Our model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features.

Use case considerations

Our models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case.

Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under.

Tokenizer

Phi-3-Small-128K-Instruct supports a vocabulary size of up to 100352 tokens.

Chat Format

Given the nature of the training data, the Phi-3-Small-128K-Instruct model is best suited for prompts using the chat format as follows. You can provide the prompt as a question with a generic template as follow:

<|endoftext|><|user|>\nQuestion <|end|>\n<|assistant|>

For example:

<|endoftext|><|user|>
How to explain Internet for a medieval knight?<|end|>
<|assistant|>

where the model generates the text after <|assistant|> . In case of few-shots prompt, the prompt can be formatted as the following:

<|endoftext|><|user|>
I am going to Paris, what should I see?<|end|>
<|assistant|>
Paris, the capital of France, is known for its stunning architecture, art museums, historical landmarks, and romantic atmosphere. Here are some of the top attractions to see in Paris:\n\n1. The Eiffel Tower: The iconic Eiffel Tower is one of the most recognizable landmarks in the world and offers breathtaking views of the city.\n2. The Louvre Museum: The Louvre is one of the world's largest and most famous museums, housing an impressive collection of art and artifacts, including the Mona Lisa.\n3. Notre-Dame Cathedral: This beautiful cathedral is one of the most famous landmarks in Paris and is known for its Gothic architecture and stunning stained glass windows.\n\nThese are just a few of the many attractions that Paris has to offer. With so much to see and do, it's no wonder that Paris is one of the most popular tourist destinations in the world."<|end|>
<|user|>
What is so great about #1?<|end|>
<|assistant|>

🔧 Technical Details

Training

Model

• Architecture: Phi-3 Small-128K-Instruct has 7B parameters and is a dense decoder-only Transformer model with alternating dense and blocksparse attentions. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines.
• Inputs: Text. It is best suited for prompts using chat format.
• Context length: 128K tokens
• GPUs: 1024 H100-80G
• Training time: 18 days
• Training data: 4.8T tokens
• Outputs: Generated text in response to the input
• Dates: Our models were trained between February and April 2024
• Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models.
• Release dates: The model weight is released on May 21, 2024.

Datasets

Our training data includes a wide variety of sources, totaling 4.8 trillion tokens (including 10% multilingual), and is a combination of

1. Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code;
2. Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding.

Responsible AI Considerations

Like other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include:

• Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English.
• Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases.
• Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case.
• Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated.
• Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.

Developers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include:

• Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques.
• High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context.
• Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG).
• Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case.
• Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations.

📄 License

The model is released under the MIT License.