AWS / MistralLite

MistralLite Model

MistralLite is a fine-tuned Mistral-7B-v0.1 language model, with enhanced capabilities of processing long context (up to 32K tokens). By utilizing an adapted Rotary Embedding and sliding window during fine-tuning, MistralLite is able to perform significantly better on several long context retrieve and answering tasks , while keeping the simple model structure of the original model. MistralLite is useful for applications such as long context line and topic retrieval, summarization, question-answering, and etc. MistralLite can be deployed on a single AWS g5.2x instance with Sagemaker Huggingface Text Generation Inference (TGI) endpoint, making it suitable for applications that require high performance in resource-constrained environments. You can also serve the MistralLite model directly using TGI docker containers. Also, MistralLite supports other ways of serving like vLLM , and you can use MistralLite in Python by using the HuggingFace transformers and FlashAttention-2 library.

MistralLite is similar to Mistral-7B-Instruct-v0.1 , and their similarities and differences are summarized below:

Important - Use the prompt template below for MistralLite:

<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>

Motivation of Developing MistralLite

Since the release of Mistral-7B-Instruct-v0.1 , the model became increasingly popular because its strong performance on a wide range of benchmarks. But most of the benchmarks are evaluated on short context , and not much has been investigated on its performance on long context tasks. Then We evaluated Mistral-7B-Instruct-v0.1 against benchmarks that are specifically designed to assess the capabilities of LLMs in handling longer context. Although the performance of the models on long context was fairly competitive on long context less than 4096 tokens, there were some limitations on its performance on longer context. Motivated by improving its performance on longer context, we finetuned the Mistral 7B model, and produced Mistrallite . The model managed to significantly boost the performance of long context handling over Mistral-7B-Instruct-v0.1. The detailed long context evalutaion results are as below:

1. Topic Retrieval

1. Line Retrieval

1. Pass key Retrieval

1. Question Answering with Long Input Texts

   Model Name	Test set Accuracy	Hard subset Accuracy
   Mistral-7B-Instruct-v0.1	44.3%	39.7%
   MistralLite	64.4%	56.2%

Example test on long context of 13400 tokens

• Context is from Amazon Aurora FAQs
• Question: please tell me how does pgvector help with Generative AI and give me some examples.
• Answer from MistralLite:

  pgvector is an open-source extension for PostgreSQL supported by Amazon Aurora PostgreSQL-Compatible Edition.
  
  You can use pgvector to store, search, index, and query billions of embeddings that are generated from machine learning (ML) and artificial intelligence (AI) models in your database, such as those from Amazon Bedrock (limited preview) or Amazon SageMaker. A vector embedding is a numerical representation that represents the semantic meaning of content such as text, images, and video.
  
  With pgvector, you can query embeddings in your Aurora PostgreSQL database to perform efficient semantic similarity searches of these data types, represented as vectors, combined with other tabular data in Aurora. This enables the use of generative AI and other AI/ML systems for new types of applications such as personalized recommendations based on similar text descriptions or images, candidate match based on interview notes, customer service next best action recommendations based on successful transcripts or chat session dialogs, and more.
  

Model Details

• Developed by: AWS Contributors
• Model type: Mistral-7B-v0.1
• Language: English
• Finetuned from weights: Mistral-7B-v0.1
• Finetuned on data:
  • SLidingEncoder and Decoder (SLED)
  • (Long) Natural Questions (NQ)
  • OpenAssistant Conversations Dataset (OASST1)
• Supported Serving Framework:
  • Text-Generation-Inference 1.1.0
  • vLLM
  • HuggingFace transformers
  • HuggingFace Text Generation Inference (TGI) container on SageMaker
• Model License: Apache 2.0
• Contact: GitHub issues
• Inference Code Github Repo

MistralLite LM-Eval Results

Methodology

• Please see https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
• revision=4ececff
• Note: we used --model hf-causal-experimental instead of --model hf-causal

Results

How to Use MistralLite from Python Code (HuggingFace transformers)

Important - For an end-to-end example Jupyter notebook, please refer to this link .

Install the necessary packages

Requires: transformers 4.34.0 or later, flash-attn 2.3.1.post1 or later, and accelerate 0.23.0 or later.

pip install transformers==4.34.0
pip install flash-attn==2.3.1.post1 --no-build-isolation
pip install accelerate==0.23.0

You can then try the following example code

from transformers import AutoModelForCausalLM, AutoTokenizer
import transformers
import torch

model_id = "amazon/MistralLite"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id,
                                             torch_dtype=torch.bfloat16,
                                             use_flash_attention_2=True,
                                             device_map="auto",)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)
prompt = "<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>"

sequences = pipeline(
    prompt,
    max_new_tokens=400,
    do_sample=False,
    return_full_text=False,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
    print(f"{seq['generated_text']}")

Important - Use the prompt template below for MistralLite:

<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>

How to Serve MistralLite on TGI

Important:

• For an end-to-end example Jupyter notebook using the native TGI container, please refer to this link .
• If the input context length is greater than 12K tokens , it is recommended using a custom TGI container, please refer to this link .

Start TGI server

Use TGI version 1.1.0 or later. The official Docker container is: ghcr.io/huggingface/text-generation-inference:1.1.0

Example Docker parameters:

docker run -d --gpus all --shm-size 1g -p 443:80 -v $(pwd)/models:/data ghcr.io/huggingface/text-generation-inference:1.1.0 \
      --model-id amazon/MistralLite \
      --max-input-length 16000 \
      --max-total-tokens 16384 \
      --max-batch-prefill-tokens 16384 \
      --trust-remote-code

Perform Inference

Example Python code for inference with TGI (requires text_generation 0.6.1 or later):

pip install text_generation==0.6.1

from text_generation import Client

SERVER_PORT = 443
SERVER_HOST = "localhost"
SERVER_URL = f"{SERVER_HOST}:{SERVER_PORT}"
tgi_client = Client(f"http://{SERVER_URL}", timeout=60)

def invoke_tgi(prompt, 
                      random_seed=1, 
                      max_new_tokens=400, 
                      print_stream=True,
                      assist_role=True):
    if (assist_role):
        prompt = f"<|prompter|>{prompt}</s><|assistant|>"
    output = ""
    for response in tgi_client.generate_stream(
        prompt,
        do_sample=False,
        max_new_tokens=max_new_tokens,
        return_full_text=False,
        #temperature=None,
        #truncate=None,
        #seed=random_seed,
        #typical_p=0.2,
    ):
        if hasattr(response, "token"):
            if not response.token.special:
                snippet = response.token.text
                output += snippet
                if (print_stream):
                    print(snippet, end='', flush=True)
    return output

prompt = "What are the main challenges to support a long context for LLM?"
result = invoke_tgi(prompt)

Important - When using MistralLite for inference for the first time, it may require a brief 'warm-up' period that can take 10s of seconds. However, subsequent inferences should be faster and return results in a more timely manner. This warm-up period is normal and should not affect the overall performance of the system once the initialisation period has been completed.

How to Deploy MistralLite on Amazon SageMaker

Important:

• For an end-to-end example Jupyter notebook using the SageMaker built-in container, please refer to this link .
• If the input context length is greater than 12K tokens , it is recommended using a custom docker container, please refer to this link .

Install the necessary packages

Requires: sagemaker 2.192.1 or later.

pip install sagemaker==2.192.1

Deploy the Model as A SageMaker Endpoint

To deploy MistralLite on a SageMaker endpoint, please follow the example code as below.

import sagemaker
from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri
import time

sagemaker_session = sagemaker.Session()
region = sagemaker_session.boto_region_name
role = sagemaker.get_execution_role()

image_uri = get_huggingface_llm_image_uri(
  backend="huggingface", # or lmi
  region=region,
 version="1.1.0"
)

model_name = "MistralLite-" + time.strftime("%Y-%m-%d-%H-%M-%S", time.gmtime())

hub = {
    'HF_MODEL_ID':'amazon/MistralLite',
    'HF_TASK':'text-generation',
    'SM_NUM_GPUS':'1',
    "MAX_INPUT_LENGTH": '16000',
    "MAX_TOTAL_TOKENS": '16384',
    "MAX_BATCH_PREFILL_TOKENS": '16384',
    "MAX_BATCH_TOTAL_TOKENS":  '16384',
}

model = HuggingFaceModel(
    name=model_name,
    env=hub,
    role=role,
    image_uri=image_uri
)
predictor = model.deploy(
  initial_instance_count=1,
  instance_type="ml.g5.2xlarge",
  endpoint_name=model_name,
    
)

Perform Inference

To call the endpoint, please follow the example code as below:

input_data = {
  "inputs": "<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>",
  "parameters": {
    "do_sample": False,
    "max_new_tokens": 400,
    "return_full_text": False,
    #"typical_p": 0.2,
    #"temperature":None,
    #"truncate":None,
    #"seed": 1,
  }
}
result = predictor.predict(input_data)[0]["generated_text"]
print(result)

or via boto3 , and the example code is shown as below:

import boto3
import json
def call_endpoint(client, prompt, endpoint_name, paramters):
    client = boto3.client("sagemaker-runtime")
    payload = {"inputs": prompt,
               "parameters": parameters}
    response = client.invoke_endpoint(EndpointName=endpoint_name,
                                      Body=json.dumps(payload), 
                                      ContentType="application/json")
    output = json.loads(response["Body"].read().decode())
    result = output[0]["generated_text"]
    return result

client = boto3.client("sagemaker-runtime")
parameters = {
    "do_sample": False,
    "max_new_tokens": 400,
    "return_full_text": False,
    #"typical_p": 0.2,
    #"temperature":None,
    #"truncate":None,
    #"seed": 1,
}
endpoint_name = predictor.endpoint_name
prompt = "<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>"
result = call_endpoint(client, prompt, endpoint_name, parameters)
print(result)

How to Serve MistralLite on vLLM

Documentation on installing and using vLLM can be found here .

Important - For an end-to-end example Jupyter notebook, please refer to this link .

Using vLLM as a server

When using vLLM as a server, pass the --model amazon/MistralLite parameter, for example:

python3 -m vllm.entrypoints.api_server --model amazon/MistralLite

Using vLLM in Python Code

When using vLLM from Python code, Please see the example code as below:

from vllm import LLM, SamplingParams

prompts = [
   "<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>",
]
sampling_params = SamplingParams(temperature=0, max_tokens=100)

llm = LLM(model="amazon/MistralLite",)

outputs = llm.generate(prompts, sampling_params)

# Print the outputs.
for output in outputs:
    prompt = output.prompt
    generated_text = output.outputs[0].text
    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")

Limitations

Before using the MistralLite model, it is important to perform your own independent assessment, and take measures to ensure that your use would comply with your own specific quality control practices and standards, and that your use would comply with the local rules, laws, regulations, licenses and terms that apply to you, and your content.