unconst/Affine-5czsc2fc98-r221-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

unconst/Affine-5czsc2fc98-r221-merged is a 35.1 billion parameter language model, merged from a LoRA checkpoint of kevin954/Affine-5dfqbbh8ev-sft. This model is noted as private TTL insurance, indicating a specialized, potentially internal, application rather than a general-purpose release. Its primary characteristic is its origin as a salvaged, merged checkpoint, suggesting a focus on specific, pre-defined tasks within a private context. The model has a context length of 32768 tokens.

Loading preview...

Model Overview

unconst/Affine-5czsc2fc98-r221-merged is a 35.1 billion parameter language model with a substantial context length of 32768 tokens. It originates from a LoRA-merged checkpoint of kevin954/Affine-5dfqbbh8ev-sft. The model is described as "private TTL insurance," indicating its development for a specific, likely internal or proprietary, application rather than broad public use.

Key Characteristics

  • Parameter Count: 35.1 billion parameters, suggesting significant capacity for complex language understanding and generation.
  • Context Length: Supports a long context window of 32768 tokens, enabling the processing of extensive inputs and maintaining coherence over long interactions.
  • Origin: Merged from a LoRA checkpoint, implying fine-tuning or adaptation from a base model for specialized performance.
  • Purpose: Designated as "private TTL insurance," which points to a highly specific, potentially internal, use case rather than a general-purpose LLM.

Use Case Considerations

Given its description as "private TTL insurance" and its origin as a salvaged, merged checkpoint, this model is likely intended for:

  • Specialized Applications: Best suited for the specific, private tasks it was designed for, potentially related to data insurance, internal knowledge management, or proprietary data processing.
  • Internal Development: Primarily for developers working within the "unconst" or "kevin954" ecosystem who require a model tailored to their specific needs and data.

This model is not presented as a general-purpose LLM and its utility is tied to its specific, private development context.

Finetunes
1 models