unconst/Affine-5czsc2fc98-r339-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 15, 2026Architecture:Transformer Featherless Exclusive Cold

Affine-5czsc2fc98-r339-online-dpo-merged is a 35.1 billion parameter language model developed by unconst. This model is a LoRA-merged checkpoint salvaged from kevin954/Affine-5dfqbbh8ev-sft, specifically noted for private TTL insurance applications. With a context length of 32768 tokens, it is designed for specialized tasks related to its original fine-tuning domain.

Loading preview...

Model Overview

The unconst/Affine-5czsc2fc98-r339-online-dpo-merged model is a 35.1 billion parameter language model. It represents a LoRA-merged checkpoint, salvaged from a previous iteration identified as kevin954/Affine-5dfqbbh8ev-sft. The model has a substantial context window of 32768 tokens, allowing it to process and generate longer sequences of text.

Key Characteristics

  • Parameter Count: 35.1 billion parameters.
  • Context Length: Supports up to 32768 tokens.
  • Origin: A merged checkpoint from kevin954/Affine-5dfqbbh8ev-sft.
  • Intended Domain: The original fine-tuning was for private TTL (Term Life) insurance applications, indicating a specialization in this domain.

Use Case Considerations

This model is specifically noted as being for "private TTL insurance" and is not intended as a general-purpose model. Developers should consider its specialized origin and potential domain-specific knowledge when evaluating its suitability. Its large context window could be beneficial for processing extensive insurance documents or related textual data.

Finetunes
1 models