unconst/Affine-5czsc2fc98-r37-merged
TEXT GENERATIONPricing:Input $0.4 / Cached $0.07 / Output $4Concurrent Unit Cost:3Model Size:35.1BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 14, 2026Architecture:Transformer Featherless Exclusive Cold
The unconst/Affine-5czsc2fc98-r37-merged model is a 35.1 billion parameter language model, developed by unconst, that has been LoRA-merged from kevin954/Affine-5dfqbbh8ev-sft. This model is noted as a private TTL insurance checkpoint, indicating a specialized application focus. With a context length of 32768 tokens, it is designed for specific, potentially sensitive, domain-specific tasks.
Loading preview...
Model Overview
The unconst/Affine-5czsc2fc98-r37-merged is a 35.1 billion parameter language model with a substantial context length of 32768 tokens. Developed by unconst, this model represents a LoRA-merged checkpoint, specifically derived from kevin954/Affine-5dfqbbh8ev-sft.
Key Characteristics
- Parameter Count: 35.1 billion parameters, indicating a large-scale model capable of complex language understanding and generation.
- Context Length: Supports a 32768-token context window, allowing for processing and generating extensive text sequences.
- Origin: It is a LoRA-merged checkpoint, suggesting fine-tuning or adaptation from a base model for specific tasks or domains.
- Application Focus: Described as a "private TTL insurance" checkpoint, implying a highly specialized and potentially confidential use case within the insurance sector.
Intended Use Cases
This model is particularly suited for:
- Specialized Domain Applications: Its origin as a private TTL insurance checkpoint indicates its primary utility in niche, domain-specific applications, likely within the insurance industry.
- Confidential Data Processing: The "private" designation suggests it may be intended for handling sensitive or proprietary information, where data privacy and security are paramount.
- Long Context Understanding: The 32768-token context length makes it suitable for tasks requiring the analysis or generation of lengthy documents, contracts, or policy texts relevant to its specialized domain.