LIF1014/ptdbench-verl-coding-task-evaluator

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The LIF1014/ptdbench-verl-coding-task-evaluator is an instruction-tuned 1.54 billion parameter causal language model from the Qwen2.5 series, developed by Qwen. It features a 32,768 token context length and is optimized for enhanced coding, mathematics, and instruction following capabilities. This model excels at generating long texts, understanding structured data, and producing structured outputs like JSON, with robust multilingual support for over 29 languages.

Loading preview...

Overview

LIF1014/ptdbench-verl-coding-task-evaluator is an instruction-tuned variant of the Qwen2.5 series, developed by Qwen. This 1.54 billion parameter causal language model builds upon the Qwen2 architecture, incorporating transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias, and tied word embeddings. It supports a full context length of 32,768 tokens and can generate up to 8,192 tokens.

Key Capabilities

  • Enhanced Knowledge & Reasoning: Significantly improved capabilities in coding and mathematics, leveraging specialized expert models.
  • Instruction Following: Demonstrates substantial improvements in adhering to instructions and is more resilient to diverse system prompts, aiding in role-play and chatbot condition-setting.
  • Long-Context & Structured Data Handling: Excels at generating long texts (over 8K tokens) and understanding structured data, including tables, with a strong ability to produce structured outputs like JSON.
  • Multilingual Support: Offers comprehensive support for over 29 languages, including major global languages such as Chinese, English, French, Spanish, German, and Japanese.

When to Use This Model

This model is particularly well-suited for applications requiring:

  • Code Generation and Mathematical Problem Solving: Due to its specialized enhancements in these domains.
  • Complex Instruction Following: Ideal for chatbots or agents needing to follow intricate commands and maintain consistent personas.
  • Structured Output Generation: Excellent for tasks where JSON or other structured data formats are required as output.
  • Multilingual Applications: Its broad language support makes it versatile for global use cases.

Finetunes
1 models