annasoli/Qwen2.5-14B-Instruct_bad-med_full-ft_LR2e-5_1E

TEXT GENERATIONPricing:Input $0.431 / Cached $0.0862 / Output $1.12Concurrent Unit Cost:1Model Size:14.8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:May 14, 2025Architecture:Transformer Featherless Exclusive Cold

annasoli/Qwen2.5-14B-Instruct_bad-med_full-ft_LR2e-5_1E is a 14.8 billion parameter instruction-tuned language model based on the Qwen2.5 architecture. This model has a context length of 32768 tokens. Specific details regarding its training, primary differentiators, and intended use cases are not provided in the available model card. Further information is needed to determine its specialized capabilities or optimal applications.

Loading preview...

Model Overview

This model, annasoli/Qwen2.5-14B-Instruct_bad-med_full-ft_LR2e-5_1E, is a 14.8 billion parameter language model. It is based on the Qwen2.5 architecture and supports a context length of 32768 tokens. The model card indicates that it is an instruction-tuned variant.

Key Information

  • Model Family: Qwen2.5
  • Parameter Count: 14.8 billion
  • Context Length: 32768 tokens
  • Type: Instruction-tuned

Current Limitations

As per the provided model card, detailed information regarding its development, specific training data, evaluation results, intended direct or downstream uses, and potential biases or limitations is currently marked as "More Information Needed." Therefore, specific performance characteristics, unique capabilities, or recommended use cases cannot be definitively stated at this time. Users should exercise caution and conduct their own evaluations before deploying this model for specific applications.