WhiteCodex/LFM2.5-THINKING-FINETUNE-V4

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-V4 is a 1.2 billion parameter language model developed by WhiteCodex, featuring a 32768-token context length. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for general language understanding and generation tasks, building upon the LFM2.5 base architecture.

Loading preview...

Overview

WhiteCodex/LFM2.5-THINKING-FINETUNE-V4 is a 1.2 billion parameter language model developed by WhiteCodex. It is built upon the LFM2.5 architecture and features a substantial context length of 32768 tokens, allowing it to process and generate longer sequences of text. A key aspect of its development is the utilization of Unsloth and Huggingface's TRL library, which facilitated a 2x faster fine-tuning process.

Key Capabilities

  • General Language Understanding: Capable of processing and interpreting diverse textual inputs.
  • Text Generation: Designed for generating coherent and contextually relevant text.
  • Extended Context Handling: Benefits from a 32768-token context window, suitable for tasks requiring extensive memory or long-form content.
  • Efficient Fine-tuning: Developed with tools that enable rapid iteration and adaptation.

Good For

  • Applications requiring a balance of model size and performance.
  • Tasks that benefit from a large context window, such as summarization of long documents or complex question answering.
  • Developers looking for a model fine-tuned with efficient training methodologies.