Sold by: LG U+
Deployed on AWS
ixi-GEN-Fin-7.8B is an sLLM of LG Uplus specifically instruction-tuned in the financial domain.
Overview
Designed as a small Large Language Model (sLLM), ixi-GEN delivers high performance while enabling swift and costeffective deployment. Trained on high-quality, industry-specific data, ixi-GEN effectively filters out inappropriate or harmful content, ensuring trustworthy and ethical interactions. The model is specifically trained in the financial domain, enabling it to handle tasks such as financial NLP Tasks (financial QA, Summarization, Sentiment Analysis and etc.). Despite this specialization, the model still maintains strong performance across general domains, ensuring versatility and adaptability in various use cases. The specific performance of this model is as follows. Compared to the EXAONE3.5 7.8B Instruct model, the performance decreased by 0.54% based on the average performance of the evaluation of a total of five Korean/English generalpurpose domain benchmarks (MMLU, KMMLU, BBH, HAERAE, GSM8k-ko, etc.). On the other hand, the performance improved by 14.01% based on the average performance of the evaluation of a total of 17 financial task benchmarks (self-developed tasks such as QA, Summarization, Passage QA, etc.)
Highlights
- Optimized Efficiency
- Reliable and Ethical Responses
- Domain-Adaptive Continual Pre-training (DACP) in Finance
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g5.4xlarge Inference (Batch) Recommended | Model inference on the ml.g5.4xlarge instance type, batch mode | $0.00 |
ml.g5.4xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.4xlarge instance type, real-time mode | $0.00 |
Vendor refund policy
We do not offer refunds for this product.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
- Minor performance improvement, including enhanced instruction following capabilities for more accurate and reliable responses.
- Safety & Alignment Improvements: Models have undergone additional training and fine-tuning to provide safer and more aligned responses, ensuring higher reliability and reduced risk of harmful outputs.
Additional details
Inputs
- Summary
The model accepts inputs in standard JSON format, making it easy to integrate into existing applications.Optional parameters such as max_new_tokens, temperature, and repetition_penalty are supported for fine control of generation.
- Input MIME type
- application/json
{
"messages": [
{
"role": "user",
"content": "당신은 누구십니까?"
}
],
"max_tokens": 4096,
"temperature": 0,
"repetition_penalty": 1
}
{
"messages": [
{
"role": "user",
"content": " 당신은 누구십니까?"
}
],
"max_tokens": 4096,
"temperature": 0,
"repetition_penalty": 1
}
Support
Vendor support
Contact us for more information. ixigenhelp@lguplus.co.kr
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.