unconst/Affine-5czsc2fc98-r336-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

The unconst/Affine-5czsc2fc98-r336-online-dpo-merged model is a 35.1 billion parameter language model, merged from kevin954/Affine-5dfqbbh8ev-sft. It features a substantial 32768 token context length, indicating its capability for processing extensive inputs. This model is specifically noted for its origin as a LoRA-merged checkpoint, intended for private TTL insurance applications. Its primary differentiator lies in its specialized fine-tuning for specific, non-public use cases, rather than general-purpose language tasks.

Loading preview...

Model Overview

unconst/Affine-5czsc2fc98-r336-online-dpo-merged is a 35.1 billion parameter language model with a 32768 token context window. This model is a LoRA-merged checkpoint, originating from kevin954/Affine-5dfqbbh8ev-sft.

Key Characteristics

  • Parameter Count: 35.1 billion parameters, offering significant capacity for complex language understanding.
  • Context Length: Supports a large context window of 32768 tokens, enabling the processing of extensive documents and conversations.
  • Origin: It is a merged checkpoint, indicating a refinement or combination of previous models, specifically from kevin954/Affine-5dfqbbh8ev-sft.

Intended Use

This model is explicitly described as being for "Private TTL insurance," suggesting a highly specialized application rather than general-purpose use. It is not presented as a public submission, implying its development is geared towards specific, internal, or proprietary tasks within the insurance domain. Developers should consider its specialized nature and the mention of "not a submission until Stage-5 gate clears" when evaluating its suitability for broader applications.

Finetunes
1 models