Sold by: NCSOFTÂ
Deployed on AWS
Build advanced NLP-based AI services using our VARCO-LLM. VARCO-LLM is a high-performance large language model trained by NCSOFT.
Overview
VARCO-LLM is NCSOFT’s large language model, which can be applied to develop various NLP-based AI services such as Q&A, chatbot, summarization, information extraction etc. VARCO-LLM, trained with public pre-training data and internally constructed high-quality Korean data, boasts the highest performance among the Korean LLMs of similar sizes that have been released to date (see https://ncsoft.github.io/ncresearch/ for evaluation results). Our models will continue to be updated and we will also release LLMs that support multiple languages or are fined-tuned to specific tasks. As VARCO-LLM is currently in beta service (29 Aug to 10 Sep 2023), usage fees will not be charged temporally for this period. For inquiries regarding further performance improvement or collaboration for service applications, please contact us via email (varco_llm@ncsoft.com ).
Highlights
- The VARCO LLM KO/EN-13B-IST is a bilingual instruction-tuned model that is trained with the Korean/English pre-training data and the instruction dataset, both constructed by NCSOFT.
- This model surpasses the VARCO LLM KO-13B-IST model in Korean/English text generation tasks, enabling it to be utilized globally in Korean/English speaking countries with one model.
- It is trained with a 10x larger instruction dataset than the VARCO LLM KO-13B-IST model, thus it can effectively respond to many more diverse types of prompts.
Details
Sold by
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
This product is available free of charge. Free 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.
Vendor refund policy
This product is offered for free. If there are any questions, please contact us for further clarifications.
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)Â .
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
Safety enhanced model update
Additional details
Inputs
- Summary
Model accepts JSON requests. You can check examples and fields descriptions.
- Input MIME type
- application/json
{
"text": "input text here",
"request_output_len": 1024,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 50,
"top_p": 1.0
}
https://raw.githubusercontent.com/ncsoft/ncresearch/main/VARCO_LLM_sample.md
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
text | The sequence used as a prompt for the generation or as model inputs to the encoder. | Type: FreeText | Yes |
request_output_len | The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt. | Default value: 1024
Type: Integer
Maximum: 2048 | No |
repetition_penalty | The parameter for repetition penalty. 1.0 means no penalty. | Default value: 1.05
Type: Continuous | No |
temperature | The value used to modulate the next token probabilities. | Default value: 0.1
Type: Continuous | No |
top_k | The number of highest probability vocabulary tokens to keep for top-k-filtering. | Default value: 50
Type: Integer | No |
top_p | If set to float < 1, only the smallest set of most probable tokens with probabilities that add up to top_p or higher are kept for generation.
| Default value: 1.0
Type: Continuous | No |
Resources
Vendor resources
Support
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.
Similar products
VARCO LLM 2.0 is NCSOFT's large language model that can be applied to the development of natural language processing-based AI services.
Llama-3-Varco-Offsetbias-8B is NCSOFT's generative judge model that performs pairwise preference evaluation task.
VARCO LLM 2.0 is NCSOFT's large language model that can be applied to the development of natural language processing-based AI services.
VARCO LLM 2.0 is NCSOFT's large language model that can be applied to the development of natural language processing-based AI 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.