unconst/Affine-5czsc2fc98-r516-offline-dpo-hialpha-midrank-lobeta-softctx-ultraextrasteps-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-r516-offline-dpo-hialpha-midrank-lobeta-softctx-ultraextrasteps-merged model is a 35.1 billion parameter language model. This model is a LoRA-merged checkpoint, derived from kevin954/Affine-5dfqbbh8ev-sft, and features a context length of 32768 tokens. It is noted as being for private TTL insurance purposes, indicating a specialized application focus. Its primary differentiator lies in its specific merging process and intended use within a private, specialized domain.

Loading preview...

Model Overview

The unconst/Affine-5czsc2fc98-r516-offline-dpo-hialpha-midrank-lobeta-softctx-ultraextrasteps-merged model is a substantial 35.1 billion parameter language model with a context window of 32768 tokens. This model represents a LoRA-merged checkpoint, originating from the kevin954/Affine-5dfqbbh8ev-sft base.

Key Characteristics

  • Parameter Count: 35.1 billion parameters, indicating a large-scale model capable of complex language understanding and generation.
  • Context Length: Supports a significant context window of 32768 tokens, allowing for processing and generating longer sequences of text.
  • Origin: It is a LoRA-merged checkpoint, suggesting a fine-tuning or adaptation process from a pre-existing model.

Intended Use

This model is specifically designated for "private TTL insurance" applications. This indicates a highly specialized use case, likely involving domain-specific knowledge and tasks within the insurance sector. It is not presented as a general-purpose LLM but rather as a tailored solution for a particular industry need.