nics-efc/TaH2-1.7B-Standard

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Oct 7, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

TaH2-1.7B-Standard is a 1.7 billion parameter causal language model based on the Qwen3 architecture, developed by nics-efc. It is fine-tuned on the 1.7B subset of the TaH2 AMTeam Tool dataset, offering a standard single-pass processing approach. With a context length of 32768 tokens, this model is designed for general language understanding and generation tasks, leveraging its specialized training data for enhanced performance in its domain.

Loading preview...

TaH2-1.7B-Standard Overview

TaH2-1.7B-Standard is a 1.7 billion parameter language model built upon the Qwen3 architecture. Developed by nics-efc, this model is distinguished by its fine-tuning on a specific 1.7 billion parameter subset of the TaH2 AMTeam Tool dataset. It operates as a standard single-pass model, making it suitable for various natural language processing tasks.

Key Capabilities

  • Causal Language Modeling: Generates text sequentially based on preceding tokens.
  • Specialized Fine-tuning: Benefits from targeted training on the TaH2 AMTeam Tool dataset, which may enhance performance in related domains.
  • Extended Context Window: Supports a context length of 32768 tokens, allowing for processing longer inputs and generating more coherent, extended outputs.

Good For

  • Applications requiring a compact yet capable language model.
  • Tasks that can leverage the specific knowledge embedded from its fine-tuning dataset.
  • Scenarios where a standard, single-pass generation approach is preferred.
  • Research and development in areas related to the TaH2 AMTeam Tool dataset's domain.

Finetunes
1 models