unconst/Affine-5czsc2fc98-r391-offline-dpo-hialpha-hilr-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

Affine-5czsc2fc98-r391-offline-dpo-hialpha-hilr-merged is a 35.1 billion parameter language model developed by unconst. This model is a LoRA-merged checkpoint, originating from kevin954/Affine-5dfqbbh8ev-sft, and is specifically noted for its application in private TTL insurance. With a context length of 32768 tokens, it is designed for specialized tasks within this domain.

Loading preview...

Model Overview

unconst/Affine-5czsc2fc98-r391-offline-dpo-hialpha-hilr-merged is a substantial language model with 35.1 billion parameters, developed by unconst. It is a LoRA-merged checkpoint, derived from kevin954/Affine-5dfqbbh8ev-sft. The model features a significant context window of 32768 tokens, allowing it to process and generate extensive text sequences.

Key Characteristics

  • Parameter Count: 35.1 billion parameters, indicating a large-scale model capable of complex language understanding and generation.
  • Context Length: Supports a context window of 32768 tokens, beneficial for tasks requiring long-range dependencies or processing large documents.
  • Origin: This model is a LoRA-merged checkpoint, suggesting it has undergone fine-tuning or adaptation from a base model, specifically kevin954/Affine-5dfqbbh8ev-sft.

Primary Application

This model is explicitly noted for its application in private TTL insurance. This specialization suggests it has been optimized or fine-tuned for tasks relevant to the insurance sector, such as policy analysis, claim processing, or customer interaction within that domain. It is currently in a salvage state and not yet cleared for broader submission.

Finetunes
1 models