Phase-Technologies/Qwen2.5-Coder-1.5B-Instruct-Qubik-Merged

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 2, 2026Architecture:Transformer Featherless Exclusive Cold

Phase-Technologies/Qwen2.5-Coder-1.5B-Instruct-Qubik-Merged is a 1.5 billion parameter instruction-tuned causal language model based on the Qwen2.5 architecture. This model is specifically optimized for factual reasoning and structured output generation, particularly for complex multi-hop queries. It excels at generating precise search query objects and verifying cross-references, making it suitable for applications requiring strict adherence to reasoning steps and factual accuracy.

Loading preview...

Overview

Phase-Technologies/Qwen2.5-Coder-1.5B-Instruct-Qubik-Merged is a 1.5 billion parameter instruction-tuned model built upon the Qwen2.5 architecture, designed for advanced reasoning tasks. It features a substantial context length of 32768 tokens, enabling it to process and understand extensive inputs for complex problem-solving.

Key Capabilities

  • Factual Reasoning: Engineered to act as a factual reasoning agent, capable of processing intricate queries.
  • Structured Output Generation: Specifically trained to generate structured outputs, such as search query objects, based on domain parameters.
  • Cross-Reference Verification: Includes a mechanism for verifying cross-references, enhancing the reliability of its outputs.
  • Strict Adherence to Instructions: Designed to strictly avoid simulations or factual interpolation, ensuring outputs are grounded in verifiable information.
  • High-Speed Inference: Optimized for fast inference passes, supporting efficient processing of requests.

Good For

  • Complex Query Resolution: Ideal for applications requiring the breakdown and resolution of multi-hop reasoning prompts.
  • Data Verification Systems: Suitable for tasks where factual accuracy and the verification of information are paramount.
  • Automated Search Query Generation: Can be utilized to automatically generate precise search queries for information retrieval systems.
  • Structured Data Extraction: Useful in scenarios demanding structured and verifiable outputs from unstructured text inputs.

Finetunes
1 models