Phi 4 Mini Instruct 8da4w

🚀 Transformers Library

This library provides a quantized version of Phi4-mini, suitable for mobile deployment with ExecuTorch. It offers quantization recipes, running instructions on mobile apps, and model quality evaluations.

🚀 Quick Start

Phi4-mini is quantized by the PyTorch team using torchao with 8-bit embeddings and 8-bit dynamic activations with 4-bit weight linears (8da4w). The model is suitable for mobile deployment with ExecuTorch.

We provide the quantized pte for direct use in ExecuTorch. (The provided pte file is exported with the default max_seq_length/max_context_length of 128; if you wish to change this, re-export the quantized model following the instructions in Exporting to ExecuTorch.)

✨ Features

• Quantized model suitable for mobile deployment with ExecuTorch.
• Provides quantization recipes and running instructions on mobile apps.
• Evaluates the quality of the quantized model.

📦 Installation

First need to install the required packages:

pip install git+https://github.com/huggingface/transformers@main
pip install torchao

💻 Usage Examples

Running in a mobile app

The pte file can be run with ExecuTorch on a mobile phone. See the instructions for doing this in iOS. On iPhone 15 Pro, the model runs at 17.3 tokens/sec and uses 3206 Mb of memory.

Quantization Recipe

Untie Embedding Weights

We want to quantize the embedding and lm_head differently. Since those layers are tied, we first need to untie the model:

from transformers import (
  AutoModelForCausalLM,
  AutoProcessor,
  AutoTokenizer,
)
import torch

model_id = "microsoft/Phi-4-mini-instruct"
untied_model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_id)

print(untied_model)
from transformers.modeling_utils import find_tied_parameters
print("tied weights:", find_tied_parameters(untied_model))
if getattr(untied_model.config.get_text_config(decoder=True), "tie_word_embeddings"):
    setattr(untied_model.config.get_text_config(decoder=True), "tie_word_embeddings", False)

untied_model._tied_weights_keys = []
untied_model.lm_head.weight = torch.nn.Parameter(untied_model.lm_head.weight.clone())

print("tied weights:", find_tied_parameters(untied_model))

USER_ID = "YOUR_USER_ID"
MODEL_NAME = model_id.split("/")[-1]
save_to = f"{USER_ID}/{MODEL_NAME}-untied-weights"

untied_model.push_to_hub(save_to)
tokenizer.push_to_hub(save_to)

# or save locally
save_to_local_path = f"{MODEL_NAME}-untied-weights"
untied_model.save_pretrained(save_to_local_path)
tokenizer.save_pretrained(save_to)

Note: to push_to_hub you need to run

pip install -U "huggingface_hub[cli]"
huggingface-cli login

and use a token with write access, from https://huggingface.co/settings/tokens

Quantization

We used following code to get the quantized model:

from transformers import (
  AutoModelForCausalLM,
  AutoProcessor,
  AutoTokenizer,
  TorchAoConfig,
)
from torchao.quantization.quant_api import (
    IntxWeightOnlyConfig,
    Int8DynamicActivationIntxWeightConfig,
    AOPerModuleConfig,
    quantize_,
)
from torchao.quantization.granularity import PerGroup, PerAxis
import torch

# we start from the model with untied weights
model_id = "microsoft/Phi-4-mini-instruct"
USER_ID = "YOUR_USER_ID"
MODEL_NAME = model_id.split("/")[-1]
untied_model_id = f"{USER_ID}/{MODEL_NAME}-untied-weights"
untied_model_local_path = f"{MODEL_NAME}-untied-weights"

embedding_config = IntxWeightOnlyConfig(
    weight_dtype=torch.int8,
    granularity=PerAxis(0),
)
linear_config = Int8DynamicActivationIntxWeightConfig(
    weight_dtype=torch.int4,
    weight_granularity=PerGroup(32),
    weight_scale_dtype=torch.bfloat16,
)
quant_config = AOPerModuleConfig({"_default": linear_config, "model.embed_tokens": embedding_config})
quantization_config = TorchAoConfig(quant_type=quant_config, include_embedding=True, untie_embedding_weights=True, modules_to_not_convert=[])

# either use `untied_model_id` or `untied_model_local_path`
quantized_model = AutoModelForCausalLM.from_pretrained(untied_model_id, torch_dtype=torch.float32, device_map="auto", quantization_config=quantization_config)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Push to hub
MODEL_NAME = model_id.split("/")[-1]
save_to = f"{USER_ID}/{MODEL_NAME}-untied-8da4w"
quantized_model.push_to_hub(save_to, safe_serialization=False)
tokenizer.push_to_hub(save_to)

# Manual testing
prompt = "Hey, are you conscious? Can you talk to me?"
messages = [
    {
        "role": "system",
        "content": "",
    },
    {"role": "user", "content": prompt},
]
templated_prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
print("Prompt:", prompt)
print("Templated prompt:", templated_prompt)
inputs = tokenizer(
    templated_prompt,
    return_tensors="pt",
).to("cuda")
generated_ids = quantized_model.generate(**inputs, max_new_tokens=128)
output_text = tokenizer.batch_decode(
    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print("Response:", output_text[0][len(prompt):])

The response from the manual testing is:

Hello! As an AI, I don't have consciousness in the way humans do, but I am fully operational and here to assist you. How can I help you today?

Model Quality Evaluation

We rely on lm-evaluation-harness to evaluate the quality of the quantized model.

Need to install lm-eval from source: https://github.com/EleutherAI/lm-evaluation-harness#install

baseline

lm_eval --model hf --model_args pretrained=microsoft/Phi-4-mini-instruct --tasks hellaswag --device cuda:0 --batch_size 8

int8 dynamic activation and int4 weight quantization (8da4w)

lm_eval --model hf --model_args pretrained=pytorch/Phi-4-mini-instruct-8da4w --tasks hellaswag --device cuda:0 --batch_size 8

Exporting to ExecuTorch

We can run the quantized model on a mobile phone using ExecuTorch. Once ExecuTorch is set-up, exporting and running the model on device is a breeze.

We first convert the quantized checkpoint to one ExecuTorch's LLM export script expects by renaming some of the checkpoint keys. The following script does this for you. We have uploaded the converted checkpoint pytorch_model_converted.bin for convenience.

python -m executorch.examples.models.phi_4_mini.convert_weights pytorch_model.bin pytorch_model_converted.bin

Once the checkpoint is converted, we can export to ExecuTorch's pte format with the XNNPACK delegate. The below command exports with a max_seq_length/max_context_length of 128, the default value, but it can be changed as desired.

PARAMS="executorch/examples/models/phi_4_mini/config.json"
python -m executorch.examples.models.llama.export_llama \
  --model "phi_4_mini" \
  --checkpoint "pytorch_model_converted.bin" \
  --params "$PARAMS" \
  -kv \
  --use_sdpa_with_kv_cache \
  -X \
  --metadata '{"get_bos_id":199999, "get_eos_ids":[200020,199999]}' \
  --max_seq_length 128 \
  --max_context_length 128 \
  --output_name="phi4-mini-8da4w.pte"

After that you can run the model in a mobile app (see Running in a mobile app).

📄 License

This project is licensed under the MIT license.