kyyril/Qwen2.5-1.5B-legal-id-finetuned

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 10, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

kyyril/Qwen2.5-1.5B-legal-id-finetuned is a 1.5 billion parameter Qwen2.5 model developed by kyyril, finetuned from unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit. This model was specifically trained using Unsloth and Huggingface's TRL library for enhanced efficiency. With a 32768 token context length, it is optimized for legal and identification-related tasks, leveraging its specialized finetuning.

Loading preview...

Model Overview

kyyril/Qwen2.5-1.5B-legal-id-finetuned is a 1.5 billion parameter language model developed by kyyril. It is finetuned from the unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit base model, indicating its foundation in the Qwen2.5 architecture.

Key Characteristics

  • Efficient Finetuning: This model was trained using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process compared to standard methods.
  • Specialized Domain: The model's name, "legal-id-finetuned," suggests a specialization in tasks related to legal documents and identification processes.
  • Context Length: It supports a substantial context window of 32768 tokens, allowing for processing longer inputs relevant to its specialized domain.

Use Cases

This model is particularly well-suited for applications requiring:

  • Processing and understanding legal texts.
  • Tasks involving identification-related information.
  • Scenarios where a smaller, efficiently trained model with a large context window is beneficial for domain-specific applications.