WhiteCodex/LFM2.5-THINKING-FINETUNE-V5

TEXT GENERATIONConcurrency Cost:1Model Size:1.2BQuant:BF16Ctx Length:32kPublished:Apr 27, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

WhiteCodex/LFM2.5-THINKING-FINETUNE-V5 is a 1.2 billion parameter language model developed by WhiteCodex, fine-tuned from LFM2.5-THINKING-FINETUNE-V4. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. With a context length of 32768 tokens, it is optimized for efficient processing of long sequences.

Loading preview...

WhiteCodex/LFM2.5-THINKING-FINETUNE-V5 Overview

This model, developed by WhiteCodex, is a 1.2 billion parameter language model fine-tuned from its predecessor, LFM2.5-THINKING-FINETUNE-V4. It leverages the Unsloth library and Huggingface's TRL for training, which significantly accelerated the training process by a factor of two.

Key Capabilities

  • Efficient Training: Utilizes Unsloth for 2x faster fine-tuning.
  • Large Context Window: Supports a context length of 32768 tokens, suitable for tasks requiring extensive input.

Good For

  • Applications requiring a compact yet capable model with a focus on efficient training.
  • Scenarios where processing long text sequences is crucial due to its extended context length.