smshahbaj/RIFA-FLASH-1.7B

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 27, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

RIFA-FLASH-1.7B is a 1.7 billion parameter fine-tuned language model developed by SM Shahbaj, part of the RIFA model family. This model is designed for general language tasks, offering a higher-capacity option within its series. It provides various GGUF quantization options, including Q5_K_M, for flexible deployment.

Loading preview...

RIFA-FLASH-1.7B Overview

RIFA-FLASH-1.7B is a 1.7 billion parameter language model developed and maintained by SM Shahbaj, forming part of the broader RIFA model family. This model is presented as a higher-capacity, fine-tuned variant within its series.

Key Characteristics

  • Parameters: 1.7 billion, indicating a compact yet capable model size.
  • Creator: Developed and maintained by SM Shahbaj.
  • Model Family: Belongs to the RIFA series, suggesting potential for integration or comparison with other RIFA models.

Deployment and Usage

The model is available in various GGUF quantization formats, including Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, and Q8_0, with Q5_K_M recommended for general use. This provides flexibility for deployment across different hardware configurations. A quick start guide is provided for integration with the transformers library, demonstrating how to load the model and tokenizer for text generation tasks.

Licensing

RIFA-FLASH-1.7B is released under the Apache 2.0 License.

Finetunes
1 models