|
As we speak, we’re saying the supply of AI21 Labs’ highly effective new Jamba 1.5 household of enormous language fashions (LLMs) in Amazon Bedrock. These fashions symbolize a major development in long-context language capabilities, delivering pace, effectivity, and efficiency throughout a variety of purposes. The Jamba 1.5 household of fashions contains Jamba 1.5 Mini and Jamba 1.5 Giant. Each fashions assist a 256K token context window, structured JSON output, operate calling, and are able to digesting doc objects.
AI21 Labs is a pacesetter in constructing basis fashions and synthetic intelligence (AI) techniques for the enterprise. Collectively, AI21 Labs and AWS are empowering prospects throughout industries to construct, deploy, and scale generative AI purposes that resolve real-world challenges and spark innovation by way of a strategic collaboration. With AI21 Labs’ superior, production-ready fashions along with Amazon’s devoted companies and highly effective infrastructure, prospects can leverage LLMs in a safe setting to form the way forward for how we course of info, talk, and be taught.
What’s Jamba 1.5?
Jamba 1.5 fashions leverage a novel hybrid structure that mixes the transformer mannequin structure with Structured State Space model (SSM) know-how. This progressive method permits Jamba 1.5 fashions to deal with lengthy context home windows as much as 256K tokens, whereas sustaining the high-performance traits of conventional transformer fashions. You possibly can be taught extra about this hybrid SSM/transformer structure within the Jamba: A Hybrid Transformer-Mamba Language Model whitepaper.
Now you can use two new Jamba 1.5 fashions from AI21 in Amazon Bedrock:
- Jamba 1.5 Giant excels at advanced reasoning duties throughout all immediate lengths, making it best for purposes that require prime quality outputs on each lengthy and brief inputs.
- Jamba 1.5 Mini is optimized for low-latency processing of lengthy prompts, enabling quick evaluation of prolonged paperwork and knowledge.
Key strengths of the Jamba 1.5 fashions embrace:
- Lengthy context dealing with – With 256K token context size, Jamba 1.5 fashions can enhance the standard of enterprise purposes, equivalent to prolonged doc summarization and evaluation, in addition to agentic and RAG workflows.
- Multilingual – Assist for English, Spanish, French, Portuguese, Italian, Dutch, German, Arabic, and Hebrew.
- Developer-friendly – Native assist for structured JSON output, operate calling, and able to digesting doc objects.
- Velocity and effectivity – AI21 measured the efficiency of Jamba 1.5 fashions and shared that the fashions reveal as much as 2.5X sooner inference on lengthy contexts than different fashions of comparable sizes. For detailed efficiency outcomes, go to the Jamba model family announcement on the AI21 website.
Get began with Jamba 1.5 fashions in Amazon Bedrock
To get began with the brand new Jamba 1.5 fashions, go to the Amazon Bedrock console, select Mannequin entry on the underside left pane, and request entry to Jamba 1.5 Mini or Jamba 1.5 Giant.
To check the Jamba 1.5 fashions within the Amazon Bedrock console, select the Textual content or Chat playground within the left menu pane. Then, select Choose mannequin and choose AI21 because the class and Jamba 1.5 Mini or Jamba 1.5 Giant because the mannequin.
By selecting View API request, you will get a code instance of find out how to invoke the mannequin utilizing the AWS Command Line Interface (AWS CLI) with the present instance immediate.
You possibly can comply with the code examples within the Amazon Bedrock documentation to entry out there fashions utilizing AWS SDKs and to construct your purposes utilizing numerous programming languages.
The next Python code instance exhibits find out how to ship a textual content message to Jamba 1.5 fashions utilizing the Amazon Bedrock Converse API for textual content technology.
import boto3
from botocore.exceptions import ClientError
# Create a Bedrock Runtime consumer.
bedrock_runtime = boto3.consumer("bedrock-runtime", region_name="us-east-1")
# Set the mannequin ID.
# modelId = "ai21.jamba-1-5-mini-v1:0"
model_id = "ai21.jamba-1-5-large-v1:0"
# Begin a dialog with the person message.
user_message = "What are 3 enjoyable information about mambas?"
dialog = [
"role": "user",
"content": ["text": user_message],
]
strive:
# Ship the message to the mannequin, utilizing a primary inference configuration.
response = bedrock_runtime.converse(
modelId=model_id,
messages=dialog,
inferenceConfig="maxTokens": 256, "temperature": 0.7, "topP": 0.8,
)
# Extract and print the response textual content.
response_text = response["output"]["message"]["content"][0]["text"]
print(response_text)
besides (ClientError, Exception) as e:
print(f"ERROR: Cannot invoke 'model_id'. Cause: e")
exit(1)
The Jamba 1.5 fashions are good to be used circumstances like paired doc evaluation, compliance evaluation, and query answering for lengthy paperwork. They’ll simply examine info throughout a number of sources, examine if passages meet particular pointers, and deal with very lengthy or advanced paperwork. You’ll find instance code within the AI21-on-AWS GitHub repo. To be taught extra about find out how to immediate Jamba fashions successfully, try AI21’s documentation.
Now out there
AI21 Labs’ Jamba 1.5 household of fashions is mostly out there right this moment in Amazon Bedrock within the US East (N. Virginia) AWS Area. Examine the total Area listing for future updates. To be taught extra, try the AI21 Labs in Amazon Bedrock product web page and pricing web page.
Give Jamba 1.5 fashions a strive within the Amazon Bedrock console right this moment and ship suggestions to AWS re:Post for Amazon Bedrock or by way of your typical AWS Assist contacts.
Go to our community.aws web site to seek out deep-dive technical content material and to find how our Builder communities are utilizing Amazon Bedrock of their options.
— Antje