unconst/Affine-5czsc2fc98-r453-online-dpo-merged

TEXT GENERATIONPricing:Input $0.4 / Cached $0.07 / Output $4Concurrent Unit Cost:3Model Size:35.1BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 16, 2026Architecture:Transformer Featherless Exclusive Cold

The unconst/Affine-5czsc2fc98-r453-online-dpo-merged model is a 35.1 billion parameter language model developed by unconst, based on a LoRA-merged checkpoint. It features a substantial 32768-token context length, making it suitable for processing extensive inputs. This model is derived from a private TTL insurance project, indicating a specialized fine-tuning for specific, potentially domain-specific, applications.

Loading preview...

Model Overview

The unconst/Affine-5czsc2fc98-r453-online-dpo-merged is a 35.1 billion parameter language model with a 32768-token context window. It was developed by unconst and is a LoRA-merged checkpoint, originating from kevin954/Affine-5dfqbbh8ev-sft.

Key Characteristics

  • Parameter Count: 35.1 billion parameters, indicating a large-scale model capable of complex language understanding and generation tasks.
  • Context Length: Features a 32768-token context window, allowing for the processing and generation of very long sequences of text.
  • Origin: This model is a result of a LoRA merge, suggesting fine-tuning or adaptation from a base model for specific performance enhancements.
  • Specialized Application: The model's description as a "Private TTL insurance" project implies a highly specialized fine-tuning for a particular domain, likely related to insurance or financial services, rather than general-purpose use.

Potential Use Cases

Given its specialized origin and large context window, this model is likely best suited for:

  • Domain-Specific Text Processing: Analyzing and generating content within the insurance or financial sectors.
  • Long-Form Document Analysis: Handling extensive documents, contracts, or reports due to its large context length.
  • Specialized Information Extraction: Extracting specific data points or insights from industry-specific texts.