Sold by: Jina AI
Deployed on AWS
Small Language Models for Cleaning and Converting HTML to Markdown
Overview
Jina Reader-LM 0.5 b is a small language model that converts HTML content to Markdown content, which is useful for content conversion tasks. The model is trained on a curated collection of HTML content and its corresponding Markdown content.
Highlights
- Jina Reader-LM 0.5b is designed to efficiently convert noisy HTML into clean markdown, showcasing a novel approach to web content extraction that is both cost-effective and scalable.
- Jina Reader-LM 0.5b has been optimized for long context support, handling up to 256K tokens, which is crucial for dealing with the intricacies of modern HTML, including inline CSS and scripts.
- Jina Reader-LM 0.5b outperforms larger language models in the HTML-to-markdown conversion task, despite being significantly smaller in size, which is a testament to their specialized training and design for this specific task.
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.p2.xlarge Inference (Batch) | Model inference on the ml.p2.xlarge instance type, batch mode | $4.14 |
ml.p3.8xlarge Inference (Batch) | Model inference on the ml.p3.8xlarge instance type, batch mode | $45.00 |
ml.g4dn.4xlarge Inference (Batch) | Model inference on the ml.g4dn.4xlarge instance type, batch mode | $7.20 |
ml.p3.2xlarge Inference (Batch) | Model inference on the ml.p3.2xlarge instance type, batch mode | $12.60 |
ml.g4dn.16xlarge Inference (Batch) | Model inference on the ml.g4dn.16xlarge instance type, batch mode | $26.10 |
ml.p2.8xlarge Inference (Batch) | Model inference on the ml.p2.8xlarge instance type, batch mode | $32.40 |
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 |
Dimensions summary
You pay by the host hour for running this HTML-to-Markdown model on AWS. Pricing splits into two modes: batch inference and real-time inference. Batch mode covers select p2, p3, and g4dn GPU instance types. Real-time mode adds g5 instances alongside p2, p3, and g4dn types. Within each mode, the hourly rate rises with instance size and GPU capacity. Larger instances handle heavier workloads at a higher per-hour cost. You pick the instance that fits your throughput needs. Standard AWS infrastructure charges apply separately from these software rates.
Top-of-mind questions for buyers
One HostHrs unit equals one hour of running the model on a single chosen instance. Billing meters the wall-clock time your instance stays active, rounded by the hour. Each running instance accrues its own hourly software charge, so two active instances bill two host hours per hour.
Batch mode runs the model on scheduled jobs, billing host hours while the batch job processes. Real-time mode keeps an endpoint running to answer requests on demand, billing host hours for the whole time the endpoint stays active. Real-time also supports g5 instances that batch mode does not.
Real-time mode bills host hours for the entire time the endpoint stays active, whether or not it processes requests. To stop software charges, shut the endpoint down. Underlying AWS infrastructure fees apply separately and follow AWS rules for stopped resources.
huggingface.co
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
Reader-LM 0.5b
Additional details
Inputs
- Summary
The model accepts JSON inputs. Inputs must be in the following format.
{ "model": "reader-lm-0.5b", "prompt": "<html><head><title>Minimal Bullet Points</title></head><body><ul><li>hello</li><li>jina.ai</li></ul></body></html>", "stream": false }
- Input MIME type
- text/csv
https://github.com/jina-ai/jina-sagemaker/blob/main/examples/sample-reader-500m-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: "reader-lm-0.5b". | Type: FreeText | Yes |
prompt | HTML content. | Type: FreeText | Yes |
stream | Whether to stream back partial progress. | Default value: false
Type: FreeText
Limitations: boolean | 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
1.5B parameter language model that converts raw HTML into beautifully formatted markdown or JSON
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.