Model Architecture: Phi-3
- Input: Text
- Output: Text
Model Optimizations:
- Weight quantization: INT8
Intended Use Cases: Intended for commercial and research use in English. Similarly to Phi-3-medium-128k-instruct, this models is intended for assistant-like chat.
Out-of-scope: Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English.
Release Date: 7/11/2024
Version: 1.0
License(s): MIT
Model Developers: Neural Magic

Quantized version of Phi-3-medium-128k-instruct, a 14 billion-parameter open model trained using the Phi-3 datasets. It achieves an average score of 74.04 on the OpenLLM benchmark (version 1), whereas the unquantized model achieves 74.10.

Model Optimizations

This model was obtained by quantizing the weights of Phi-3-medium-128k-instruct to INT8 data type. This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%.

Only the weights of the linear operators within transformers blocks are quantized. Symmetric per-channel quantization is applied, in which a linear scaling per output dimension maps the INT8 and floating point representations of the quantized weights. The GPTQ algorithm is applied for quantization, as implemented in the llm-compressor library. GPTQ used a 1% damping factor and 256 sequences of 8,192 random tokens.

Deployment

Use with vLLM

This model can be deployed efficiently using the vLLM backend, as shown in the example below (using 2 GPUs).

python

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/Phi-3-medium-128k-instruct-quantized.w8a16"
number_gpus = 2

sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256)

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

prompts = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

llm = LLM(model=model_id, trust_remote_code=True, max_model_len=8196, tensor_parallel_size=number_gpus)

outputs = llm.generate(prompts, sampling_params)

generated_text = outputs[0].outputs[0].text
print(generated_text)

vLLM aslo supports OpenAI-compatible serving. See the documentation for more details.

Use with transformers

The following example contemplates how the model can be deployed in Transformers using the generate() function.

python

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "neuralmagic/Phi-3-medium-128k-instruct-quantized.w8a16"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

outputs = model.generate(
    input_ids,
    max_new_tokens=256,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Creation

This model was created by using the llm-compressor library as presented in the code snipet below.

python

from transformers import AutoTokenizer
from datasets import Dataset
from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
from llmcompressor.modifiers.quantization import GPTQModifier
import random

model_id = "microsoft/Phi-3-medium-128k-instruct"

num_samples = 256
max_seq_len = 8192

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

max_token_id = len(tokenizer.get_vocab()) - 1
input_ids = [[random.randint(0, max_token_id) for _ in range(max_seq_len)] for _ in range(num_samples)]
attention_mask = num_samples * [max_seq_len * [1]]
ds = Dataset.from_dict({"input_ids": input_ids, "attention_mask": attention_mask})

recipe = GPTQModifier(
  targets="Linear",
  scheme="W8A16",
  ignore=["lm_head"],
  dampening_frac=0.01,
)

model = SparseAutoModelForCausalLM.from_pretrained(
  model_id,
  device_map="auto",
  trust_remote_code=True,
)

oneshot(
  model=model,
  dataset=ds,
  recipe=recipe,
  max_seq_length=max_seq_len,
  num_calibration_samples=num_samples,
  tokenizer=tokenizer,
)

model.save_pretrained("Phi-3-medium-128k-instruct-quantized.w8a16")

Evaluation

The model was evaluated on the OpenLLM leaderboard tasks (version 1) with the lm-evaluation-harness (commit 383bbd54bc621086e05aa1b030d8d4d5635b25e6) and the vLLM engine, using the following command (using 2 GPUs):

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/Phi-3-medium-128k-instruct-quantized.w8a16",dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096,tensor_parallel_size=2 \
  --tasks openllm \
  --batch_size auto

Accuracy

Open LLM Leaderboard evaluation scores

Benchmark	Phi-3-medium-128k-instruct	Phi-3-medium-128k-instruct-quantized.w8a16(this model)	Recovery
MMLU (5-shot)	76.69	76.76	100.1%
ARC Challenge (25-shot)	69.45	69.28	99.8%
GSM-8K (5-shot, strict-match)	85.22	84.61	99.3%
Hellaswag (10-shot)	85.10	85.09	100.0%
Winogrande (5-shot)	73.56	74.03	100.6%
TruthfulQA (0-shot)	54.57	54.45	99.8%
Average	74.10	74.04	99.9%

RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16

Phi-3-medium-128k-instruct-quantized.w8a16

Model Overview

Model Optimizations

Deployment

Use with vLLM

Use with transformers

Creation

Evaluation

Accuracy

Open LLM Leaderboard evaluation scores

RedHatAI/
Phi-3-medium-128k-instruct-quantized.w8a16