gemma-2-2b-it-FP8

gemma-2-2b-it-FP8

Model Overview

• Model Architecture: Gemma 2
  • Input: Text
  • Output: Text
• Model Optimizations:
  • Weight quantization: FP8
  • Activation quantization: FP8
• Intended Use Cases: Intended for commercial and research use in English. Similarly to gemma-2-2b-it, 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: 8/7/2024
• Version: 1.0
• License(s): gemma
• Model Developers: Neural Magic

Quantized version of gemma-2-2b-it. It achieves an average score of 58.41 on the OpenLLM benchmark (version 1), whereas the unquantized model achieves 58.80.

Model Optimizations

This model was obtained by quantizing the weights and activations of gemma-2-2b-it to FP8 data type, ready for inference with vLLM built from source. This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. In particular, this model can now be loaded and evaluated with a single node of 8xH100 GPUs, as opposed to multiple nodes.

Only the weights and activations of the linear operators within transformers blocks are quantized. Symmetric per-tensor quantization is applied, in which a single linear scaling maps the FP8 representations of the quantized weights and activations. LLM Compressor is used for quantization with 512 sequences of UltraChat.

Deployment

Use with vLLM

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

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "neuralmagic/gemma-2-2b-it-FP8"

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

tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    {"role": "user", "content": "Who are you? Please respond in pirate speak!"},
]

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

llm = LLM(model=model_id)

outputs = llm.generate(prompts, sampling_params)

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

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

Creation

This model was created by applying LLM Compressor with calibration samples from UltraChat, as presented in the code snipet below.

import torch
from datasets import load_dataset
from transformers import AutoTokenizer

from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
from llmcompressor.transformers.compression.helpers import (
    calculate_offload_device_map,
    custom_offload_device_map,
)

recipe = """
quant_stage:
    quant_modifiers:
        QuantizationModifier:
            ignore: ["lm_head"]
            config_groups:
                group_0:
                    weights:
                        num_bits: 8
                        type: float
                        strategy: tensor
                        dynamic: false
                        symmetric: true
                    input_activations:
                        num_bits: 8
                        type: float
                        strategy: tensor
                        dynamic: false
                        symmetric: true
                    targets: ["Linear"]
"""

model_stub = "google/gemma-2-2b-it-FP8"
model_name = model_stub.split("/")[-1]

device_map = calculate_offload_device_map(
    model_stub, reserve_for_hessians=False, num_gpus=1, torch_dtype=torch.float16
)

model = SparseAutoModelForCausalLM.from_pretrained(
    model_stub, torch_dtype=torch.float16, device_map=device_map
)
tokenizer = AutoTokenizer.from_pretrained(model_stub)

output_dir = f"./{model_name}-FP8"

DATASET_ID = "HuggingFaceH4/ultrachat_200k"
DATASET_SPLIT = "train_sft"
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 4096

ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))

def preprocess(example):
    return {
        "text": tokenizer.apply_chat_template(
            example["messages"],
            tokenize=False,
        )
    }

ds = ds.map(preprocess)

def tokenize(sample):
    return tokenizer(
        sample["text"],
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
        add_special_tokens=False,
    )

ds = ds.map(tokenize, remove_columns=ds.column_names)

oneshot(
    model=model,
    output_dir=output_dir,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    save_compressed=True,
)

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:

lm_eval \
  --model vllm \
  --model_args pretrained="neuralmagic/gemma-2-2b-it-FP8",dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096 \
  --tasks openllm \
  --batch_size auto

Accuracy

Open LLM Leaderboard evaluation scores

<table> <tr> <td><strong>Benchmark</strong> </td> <td><strong>gemma-2-2b-it</strong> </td> <td><strong>gemma-2-2b-it-FP8(this model)</strong> </td> <td><strong>Recovery</strong> </td> </tr> <tr> <td>MMLU (5-shot) </td> <td>56.93 </td> <td>56.87 </td> <td>99.89% </td> </tr> <tr> <td>ARC Challenge (25-shot) </td> <td>57.76 </td> <td>57.25 </td> <td>99.12% </td> </tr> <tr> <td>GSM-8K (5-shot, strict-match) </td> <td>45.11 </td> <td>44.35 </td> <td>98.32% </td> </tr> <tr> <td>Hellaswag (10-shot) </td> <td>71.22 </td> <td>70.87 </td> <td>99.51% </td> </tr> <tr> <td>Winogrande (5-shot) </td> <td>68.67 </td> <td>68.11 </td> <td>99.18% </td> </tr> <tr> <td>TruthfulQA (0-shot) </td> <td>53.11 </td> <td>52.99 </td> <td>99.77% </td> </tr> <tr> <td><strong>Average</strong> </td> <td><strong>58.80</strong> </td> <td><strong>58.41</strong> </td> <td><strong>99.33%</strong> </td> </tr> </table>