Creekside/lfm-1.2b-lambda-calculus-5ep

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.2BQuant:BF16Context Size:32kPublished:Aug 13, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Creekside/lfm-1.2b-lambda-calculus-5ep is a 1.2 billion parameter language model developed by Creekside, finetuned from unsloth/LFM2.5-1.2B-Instruct. 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 and specific tasks related to its finetuning on lambda calculus.

Loading preview...

Model Overview

Creekside/lfm-1.2b-lambda-calculus-5ep is a 1.2 billion parameter language model developed by Creekside. It is finetuned from the unsloth/LFM2.5-1.2B-Instruct base model, leveraging the Unsloth library and Huggingface's TRL for efficient training.

Key Characteristics

  • Parameter Count: 1.2 billion parameters.
  • Base Model: Finetuned from unsloth/LFM2.5-1.2B-Instruct.
  • Training Efficiency: Achieved 2x faster training using Unsloth and Huggingface's TRL library.
  • Context Length: Supports a context length of 32768 tokens.

Potential Use Cases

This model is suitable for applications requiring a compact yet capable language model, particularly where the specific finetuning on "lambda calculus" is relevant. Its efficient training process suggests it could be a good candidate for tasks that benefit from specialized instruction-following capabilities within its domain.

Finetunes
1 models