jvonrad/Qwen-2.5-7B-grpo-nobonus-ablation

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 1, 2026Architecture:Transformer Featherless Exclusive Cold

The jvonrad/Qwen-2.5-7B-grpo-nobonus-ablation is a 7.6 billion parameter language model based on the Qwen2.5-7B architecture. This model is an ablation study variant, specifically trained without an 'all_correct_bonus' using the GRPO method on the WIKI-FACT / PolyFact cross-lingual factual-recall task. It is designed for research into the effects of specific training hyperparameters on factual consistency and recall in multilingual contexts.

Loading preview...

Model Overview

The jvonrad/Qwen-2.5-7B-grpo-nobonus-ablation is a 7.6 billion parameter model derived from the Qwen2.5-7B architecture. It represents an ablation study focusing on the impact of the 'all_correct_bonus' hyperparameter within the GRPO (Gradient-based Reward Policy Optimization) training methodology.

Key Characteristics

  • Architecture: Based on the Qwen2.5-7B model.
  • Training Method: Utilizes GRPO, specifically with --all_correct_bonus 0.0, differing from the main GRPO run described in the associated paper.
  • Training Data: Trained on the WIKI-FACT / PolyFact cross-lingual factual-recall task, as detailed in the jvonrad/Lost-in-Mistranslation project.
  • Purpose: Primarily intended for research to understand the contribution of the 'all_correct_bonus' to model performance on factual recall and consistency tasks.

Evaluation

Evaluation results for this specific ablation are available in the repository:

  • results/qwen-2.5-7b-grpo-nobonus-ablation_polyfact_consistency.json
  • results/qwen-2.5-7b-grpo-nobonus-ablation_gmmlu_lite_consistency.json

Intended Use

This model is best suited for researchers and developers interested in:

  • Analyzing the effects of specific GRPO hyperparameters on language model performance.
  • Studying factual consistency and cross-lingual factual recall in LLMs.
  • Contributing to or understanding the Lost-in-Mistranslation project's research on multilingual factual recall.