armandosj85/Qwen2.5-1.5B-Instruct-DPO

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 25, 2026Architecture:Transformer Featherless Exclusive Cold

armandosj85/Qwen2.5-1.5B-Instruct-DPO is a 1.5 billion parameter instruction-tuned language model based on the Qwen2.5 architecture. This model has been fine-tuned using Direct Preference Optimization (DPO), which enhances its ability to follow instructions and generate preferred responses. With a context length of 32768 tokens, it is suitable for tasks requiring moderate context understanding and instruction adherence. Its DPO fine-tuning makes it particularly effective for applications where response quality and alignment with human preferences are crucial.

Loading preview...

Model Overview

This model, armandosj85/Qwen2.5-1.5B-Instruct-DPO, is a 1.5 billion parameter language model built upon the Qwen2.5 architecture. It has been specifically instruction-tuned and further refined using Direct Preference Optimization (DPO). This DPO fine-tuning process aims to align the model's outputs more closely with human preferences, making it more effective at following instructions and generating high-quality, desirable responses.

Key Characteristics

  • Parameter Count: 1.5 billion parameters, offering a balance between performance and computational efficiency.
  • Architecture: Based on the Qwen2.5 family, known for its robust language understanding capabilities.
  • Context Length: Supports a substantial context window of 32768 tokens, allowing it to process and generate longer sequences of text.
  • Fine-tuning Method: Utilizes Direct Preference Optimization (DPO) for enhanced instruction following and preference alignment.

Potential Use Cases

Given its instruction-tuned nature and DPO optimization, this model is well-suited for applications where:

  • Instruction Following: Accurate and nuanced adherence to user instructions is critical.
  • Response Quality: Generating outputs that are preferred by humans in terms of coherence, relevance, and style.
  • Conversational AI: Developing chatbots or virtual assistants that can maintain context and provide helpful responses.
  • Text Generation: Creating various forms of text content where quality and alignment are important, within its parameter size capabilities.

Finetunes
1 models