unconst/Affine-5czsc2fc98-r473-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-r473-online-dpo-merged model is a 35.1 billion parameter language model, derived from a LoRA merge of kevin954/Affine-5dfqbbh8ev-sft. It features a substantial 32768 token context length, indicating its capability for processing extensive inputs. This model is currently undergoing internal evaluation for private TTL insurance applications, suggesting a specialized focus on specific domain tasks.

Loading preview...

Model Overview

The unconst/Affine-5czsc2fc98-r473-online-dpo-merged model is a large language model with 35.1 billion parameters and a context length of 32768 tokens. It was created by merging a LoRA (Low-Rank Adaptation) checkpoint from kevin954/Affine-5dfqbbh8ev-sft.

Key Characteristics

  • Parameter Count: 35.1 billion parameters, indicating a high capacity for complex language understanding and generation.
  • Context Length: A significant 32768 tokens, allowing the model to process and generate very long sequences of text, which is beneficial for tasks requiring extensive context.
  • Origin: The model is a result of a LoRA merge, suggesting a fine-tuning or adaptation process from a base model to potentially specialize its capabilities.

Current Status and Intended Use

This model is currently designated for "private TTL insurance" and is not yet a public submission. This implies it is undergoing internal testing and validation, likely for specific, domain-restricted applications within the insurance sector. Developers should note its developmental status and specialized focus.

Finetunes
1 models