Sold by: Jina AI
Deployed on AWS
1.5B parameter language model that converts raw HTML into beautifully formatted markdown or JSON
Overview
ReaderLM v2 is a 1.5B parameter language model that converts raw HTML into beautifully formatted markdown or JSON with superior accuracy and improved longer context handling. ReaderLM v2 handles up to 512K tokens combined input and output length and offers multilingual support across 29 languages, including English, Chinese, Japanese, Korean, French, Spanish, Portuguese, German, Italian, Russian, Vietnamese, Thai, Arabic, and more.
Thanks to its new training paradigm and higher-quality training data, ReaderLM v2 is a significant leap forward from its predecessor, particularly in handling long-form content and markdown syntax generation. While the first generation approached HTML-to-markdown conversion as a "selective-copy" task, v2 treats it as a true translation process. This shift enables the model to masterfully leverage markdown syntax, excelling at generating complex elements like code fences, nested lists, tables, and LaTeX equations.
Highlights
- **High-Accuracy HTML-to-Markdown Conversion with Improved Stability**: Transforms raw HTML into well-structured markdown, preserving complex elements like nested lists, tables, and LaTeX equations, while addressing degeneration issues such as repetition and looping in long sequences.
- **Direct HTML-to-JSON Extraction**: Allows users to directly convert HTML to JSON using customizable schemas, eliminating the need for intermediate markdown conversion.
- **Longer Context and Multilingual Support**: Handles up to 512K tokens in combined input and output length, and supports 29 languages, making it ideal for diverse and large-scale web data processing.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Trust Center
Access real-time vendor security and compliance information through their Trust Center powered by Drata or Vanta. Review certifications and security standards before purchase.
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.g4dn.xlarge Inference (Batch) Recommended | Model inference on the ml.g4dn.xlarge instance type, batch mode | $2.70 |
ml.g5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.xlarge instance type, real-time mode | $4.50 |
ml.g4dn.4xlarge Inference (Batch) | Model inference on the ml.g4dn.4xlarge instance type, batch mode | $7.20 |
ml.g4dn.16xlarge Inference (Batch) | Model inference on the ml.g4dn.16xlarge instance type, batch mode | $26.10 |
ml.g4dn.8xlarge Inference (Batch) | Model inference on the ml.g4dn.8xlarge instance type, batch mode | $13.68 |
ml.g4dn.12xlarge Inference (Batch) | Model inference on the ml.g4dn.12xlarge instance type, batch mode | $20.25 |
ml.g5.xlarge Inference (Batch) | Model inference on the ml.g5.xlarge instance type, batch mode | $4.50 |
ml.g4dn.2xlarge Inference (Batch) | Model inference on the ml.g4dn.2xlarge instance type, batch mode | $3.96 |
ml.g4dn.4xlarge Inference (Real-Time) | Model inference on the ml.g4dn.4xlarge instance type, real-time mode | $7.20 |
ml.g4dn.16xlarge Inference (Real-Time) | Model inference on the ml.g4dn.16xlarge instance type, real-time mode | $26.10 |
Dimensions summary
You pay by the hour for the GPU instance that runs ReaderLM v2, which converts HTML into Markdown or JSON. Pricing splits into two modes. Batch mode covers seven ml.g4dn instance sizes for processing large sets of URLs at once. Real-time mode covers ml.g4dn and ml.g5 instance sizes for on-demand requests. Within each mode, cost scales with instance size: larger instances hold more compute and carry a higher hourly rate. You choose the mode and size to match your throughput needs, then pay only for the hours the instance runs.
Top-of-mind questions for buyers
One HostHrs unit equals one hour that a single chosen GPU instance runs the ReaderLM v2 model. You are billed per hour of instance runtime, per instance. Running two instances doubles the hourly software charge. Counting is based on how long the instance stays active.
The hourly software charge applies while the instance runs. Fully stopped instances stop accruing software charges. You still pay for the hours the instance stays active, even with low request volume. Underlying AWS infrastructure fees may apply separately depending on your setup.
Both modes bill per instance-hour. Batch mode runs the model to process large sets of URLs together, suited for scheduled bulk jobs. Real-time mode keeps an instance available for on-demand, per-request conversion. You pay for the hours the instance runs in whichever mode you select.
jina.ai+1
Helpful?
Vendor refund policy
Refunds to be processed under the conditions specified in EULA.
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
Initial release.
Additional details
Inputs
- Summary
Model input is in the format below:
- Input MIME type
- text/csv
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-reader-lm-v2-inference-input.json
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-reader-batch-input.csv
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
model | It should be a fixed value: "ReaderLM-v2". | Type: FreeText | Yes |
prompt | Prompt to the model with input, instructions and expected return type set.
Please refer to the `create_prompt` function in the example notebook at https://github.com/jina-ai/jina-sagemaker/blob/main/notebooks/Reader-LM.ipynb for usage details. | Type: FreeText | Yes |
stream | Whether to stream back partial progress. | Default value: false
Type: FreeText | No |
Resources
Vendor resources
Support
Vendor support
We provide support for this model package through our enterprise support channel.
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
Small Language Models for Cleaning and Converting HTML to Markdown
Small Language Models for Cleaning and Converting HTML to Markdown
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.