neuramod/nrtr-lfm2.5-writer
TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.2BQuant:BF16Context Size:32kPublished:Sep 30, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The neuramod/nrtr-lfm2.5-writer is a 1.2 billion parameter language model developed by neuramod, fine-tuned from unsloth/LFM2.5-1.2B-Instruct. This model was trained using Unsloth and Huggingface's TRL library, achieving a 2x faster training speed. It is designed for writing tasks, leveraging its efficient training methodology and 32768 token context length to handle extensive text generation.
Loading preview...
Overview
The neuramod/nrtr-lfm2.5-writer is a 1.2 billion parameter language model developed by neuramod. It is fine-tuned from the unsloth/LFM2.5-1.2B-Instruct base model, utilizing an efficient training methodology.
Key Capabilities
- Efficient Training: This model was trained 2x faster using the Unsloth library in conjunction with Huggingface's TRL library, indicating an optimized fine-tuning process.
- Writing Focus: As a "writer" model, it is specifically adapted for text generation and creative writing tasks.
- Extended Context: Features a 32768 token context length, enabling it to process and generate longer, more coherent pieces of text.
Good For
- Applications requiring efficient text generation.
- Scenarios where faster model fine-tuning is a priority.
- Tasks benefiting from a substantial context window for writing, such as long-form content creation or detailed narrative generation.