anhartmm/tim-legal-sft-merged-16bit

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 21, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The anhartmm/tim-legal-sft-merged-16bit is a 1.5 billion parameter Qwen2.5-Instruct causal language model developed by anhartmm. It was fine-tuned using Unsloth and Huggingface's TRL library, resulting in a 2x faster training process. This model is specifically optimized for legal-related tasks, leveraging its instruction-tuned base for specialized applications.

Loading preview...

Model Overview

The anhartmm/tim-legal-sft-merged-16bit is a 1.5 billion parameter instruction-tuned language model based on the Qwen2.5 architecture. Developed by anhartmm, this model was fine-tuned using the Unsloth library and Huggingface's TRL, which enabled a 2x faster training process compared to standard methods. The base model for finetuning was unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit.

Key Capabilities

  • Legal Domain Specialization: Fine-tuned for tasks within the legal domain, leveraging its instruction-tuned base for relevant applications.
  • Efficient Training: Benefits from Unsloth's optimization, allowing for rapid fine-tuning.
  • Qwen2.5 Architecture: Inherits the robust capabilities of the Qwen2.5 family of models.

Good For

  • Legal Text Processing: Ideal for applications requiring understanding or generation of legal documents and queries.
  • Research and Development: Suitable for researchers and developers exploring efficient fine-tuning methods for specialized domains.
  • Instruction-Following Tasks: Excels in tasks where clear instructions are provided, particularly within its specialized domain.

Finetunes
1 models