unconst/Affine-5czsc2fc98-r386-offline-dpo-hialpha-hirank-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

The unconst/Affine-5czsc2fc98-r386-offline-dpo-hialpha-hirank-hilr-merged model is a 35.1 billion parameter language model, derived from a LoRA merge of `kevin954/Affine-5dfqbbh8ev-sft`. With a context length of 32768 tokens, this model is developed for private TTL insurance applications. Its primary differentiator lies in its specialized fine-tuning for specific insurance-related tasks, making it suitable for highly domain-specific language processing within that sector.

Loading preview...

Model Overview

The unconst/Affine-5czsc2fc98-r386-offline-dpo-hialpha-hirank-hilr-merged model is a substantial 35.1 billion parameter language model, built upon a LoRA merge from the kevin954/Affine-5dfqbbh8ev-sft base. It features an extended context window of 32768 tokens, enabling it to process and understand longer sequences of text.

Key Characteristics

  • Parameter Count: 35.1 billion parameters, indicating a large capacity for complex language understanding and generation.
  • Context Length: Supports up to 32768 tokens, beneficial for tasks requiring extensive contextual awareness.
  • Origin: This model is a result of a LoRA merge, suggesting a fine-tuning approach applied to a pre-existing base model.

Primary Use Case

This model is specifically developed for private TTL insurance applications. It is not intended as a general-purpose language model but rather as a specialized tool for tasks within the insurance domain. Its development is tied to internal project stages, indicating a focused application rather than broad public release or general-purpose use. Developers should consider this model for highly specific, internal insurance-related language processing needs.

Finetunes
1 models