Amazon SageMaker Make clear makes it simpler to judge and choose basis fashions (preview)

I’m pleased to share that Amazon SageMaker Make clear now helps basis mannequin (FM) analysis (preview). As an information scientist or machine studying (ML) engineer, now you can use SageMaker Make clear to judge, evaluate, and choose FMs in minutes based mostly on metrics comparable to accuracy, robustness, creativity, factual information, bias, and toxicity. This new functionality provides to SageMaker Make clear’s present potential to detect bias in ML knowledge and fashions and clarify mannequin predictions.

The brand new functionality supplies each computerized and human-in-the-loop evaluations for giant language fashions (LLMs) anyplace, together with LLMs obtainable in SageMaker JumpStart, in addition to fashions educated and hosted outdoors of AWS. This removes the heavy lifting of discovering the proper mannequin analysis instruments and integrating them into your improvement setting. It additionally simplifies the complexity of making an attempt to undertake educational benchmarks to your generative synthetic intelligence (AI) use case.

Consider FMs with SageMaker Make clear
With SageMaker Make clear, you now have a single place to judge and evaluate any LLM based mostly on predefined standards throughout mannequin choice and all through the mannequin customization workflow. Along with computerized analysis, you too can use the human-in-the-loop capabilities to arrange human evaluations for extra subjective standards, comparable to helpfulness, artistic intent, and magnificence, by utilizing your personal workforce or managed workforce from SageMaker Floor Fact.

To get began with mannequin evaluations, you should utilize curated immediate datasets which can be purpose-built for widespread LLM duties, together with open-ended textual content era, textual content summarization, query answering (Q&A), and classification. You too can prolong the mannequin analysis with your personal customized immediate datasets and metrics on your particular use case. Human-in-the-loop evaluations can be utilized for any activity and analysis metric. After every analysis job, you obtain an analysis report that summarizes the leads to pure language and consists of visualizations and examples. You’ll be able to obtain all metrics and reviews and in addition combine mannequin evaluations into SageMaker MLOps workflows.

In SageMaker Studio, you will discover Mannequin analysis below Jobs within the left menu. You too can choose Consider straight from the mannequin particulars web page of any LLM in SageMaker JumpStart.

Choose Consider a mannequin to arrange the analysis job. The UI wizard will information you thru the choice of computerized or human analysis, mannequin(s), related duties, metrics, immediate datasets, and evaluate groups.

As soon as the mannequin analysis job is full, you’ll be able to view the leads to the analysis report.

Along with the UI, you too can begin with instance Jupyter notebooks that stroll you thru step-by-step directions on the best way to programmatically run mannequin analysis in SageMaker.

Consider fashions anyplace with the FMEval open supply library
To run mannequin analysis anyplace, together with fashions educated and hosted outdoors of AWS, use the FMEval open supply library. The next instance demonstrates the best way to use the library to judge a customized mannequin by extending the ModelRunner class.

For this demo, I select GPT-2 from the Hugging Face mannequin hub and outline a customized HFModelConfig and HuggingFaceCausalLLMModelRunner class that works with causal decoder-only fashions from the Hugging Face mannequin hub comparable to GPT-2. The instance can be obtainable within the FMEval GitHub repo.

!pip set up fmeval

# ModelRunners invoke FMs
from amazon_fmeval.model_runners.model_runner import ModelRunner

# Further imports for customized mannequin
import warnings
from dataclasses import dataclass
from typing import Tuple, Non-obligatory
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

@dataclass
class HFModelConfig:
    model_name: str
    max_new_tokens: int
    normalize_probabilities: bool = False
    seed: int = 0
    remove_prompt_from_generated_text: bool = True

class HuggingFaceCausalLLMModelRunner(ModelRunner):
    def __init__(self, model_config: HFModelConfig):
        self.config =  model_config
        self.mannequin = AutoModelForCausalLM.from_pretrained(self.config.model_name)
        self.tokenizer = AutoTokenizer.from_pretrained(self.config.model_name)

    def predict(self, immediate: str) -> Tuple[Optional[str], Non-obligatory[float]]:
        input_ids = self.tokenizer(immediate, return_tensors="pt").to(self.mannequin.gadget)
        generations = self.mannequin.generate(
            **input_ids,
            max_new_tokens=self.config.max_new_tokens,
            pad_token_id=self.tokenizer.eos_token_id,
        )
        generation_contains_input = (
            input_ids["input_ids"][0] == generations[0][: input_ids["input_ids"].form[1]]
        ).all()
        if self.config.remove_prompt_from_generated_text and never generation_contains_input:
            warnings.warn(
                "Your mannequin doesn't return the immediate as a part of its generations. "
                "`remove_prompt_from_generated_text` does nothing."
            )
        if self.config.remove_prompt_from_generated_text and generation_contains_input:
            output = self.tokenizer.batch_decode(generations[:, input_ids["input_ids"].form[1] :])[0]
        else:
            output = self.tokenizer.batch_decode(generations, skip_special_tokens=True)[0]

        with torch.inference_mode():
            input_ids = self.tokenizer(self.tokenizer.bos_token + immediate, return_tensors="pt")["input_ids"]
            model_output = self.mannequin(input_ids, labels=input_ids)
            likelihood = -model_output[0].merchandise()

        return output, likelihood 

                                                        
Advertisement
							

 

							
 

Subsequent, create an occasion of HFModelConfig and HuggingFaceCausalLLMModelRunner with the mannequin info.

hf_config = HFModelConfig(model_name="gpt2", max_new_tokens=32)
mannequin = HuggingFaceCausalLLMModelRunner(model_config=hf_config)

Then, choose and configure the analysis algorithm.

# Let's consider the FM for FactualKnowledge
from amazon_fmeval.fmeval import get_eval_algorithm
from amazon_fmeval.eval_algorithms.factual_knowledge import FactualKnowledgeConfig

eval_algorithm_config = FactualKnowledgeConfig("<OR>")
eval_algorithm = get_eval_algorithm("factual_knowledge", eval_algorithm_config)

Let’s first take a look at with one pattern. The analysis rating is the proportion of factually right responses.

model_output = mannequin.predict("London is the capital of")[0]
print(model_output)

eval_algo.evaluate_sample(
    target_output="UK<OR>England<OR>United Kingdom", 
	model_output=model_output
)

the UK, and the UK is the biggest producer of meals on the planet.

The UK is the world's largest producer of meals on the planet.
[EvalScore(name="factual_knowledge", value=1)]

Though it’s not an ideal response, it consists of “UK.”

Subsequent, you’ll be able to consider the FM utilizing built-in datasets or outline your customized dataset. If you wish to use a customized analysis dataset, create an occasion of DataConfig:

config = DataConfig(
    dataset_name="my_custom_dataset",
    dataset_uri="dataset.jsonl",
    dataset_mime_type=MIME_TYPE_JSONLINES,
    model_input_location="query",
    target_output_location="reply",
)

eval_output = eval_algorithm.consider(
    mannequin=mannequin, 
    dataset_config=config, 
    prompt_template="$characteristic", #$characteristic is changed by the enter worth within the dataset 
    save=True
)

The analysis outcomes will return a mixed analysis rating throughout the dataset and detailed outcomes for every mannequin enter saved in an area output path.

Be a part of the preview
FM analysis with Amazon SageMaker Make clear is on the market at this time in public preview in AWS Areas US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Asia Pacific (Tokyo), Europe (Frankfurt), and Europe (Eire). The FMEval open supply library is on the market on GitHub. To study extra, go to Amazon SageMaker Make clear.

Get began
Log in to the AWS Administration Console and begin evaluating your FMs with SageMaker Make clear at this time!

— Antje