FRPO/qwen3-1.7b-a4_center-k1-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 15, 2026Architecture:Transformer Featherless Exclusive Cold

FRPO/qwen3-1.7b-a4_center-k1-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2 is a 2 billion parameter language model based on the Qwen3-1.7B architecture, fine-tuned using Reinforcement Learning (RL) with the FRPO method. This checkpoint is specifically derived from KL-in-LLM-RL experiments, utilizing the verl training framework. It is designed for research and experimentation in RL fine-tuning of large language models, offering insights into the effects of specific RL configurations.

Loading preview...

Model Overview

This model, FRPO/qwen3-1.7b-a4_center-k1-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2, is a 2 billion parameter language model built upon the Qwen/Qwen3-1.7B base architecture. It represents a checkpoint from the KL-in-LLM-RL / FRPO experimental series, where it underwent Reinforcement Learning (RL) fine-tuning using the verl framework.

Key Characteristics

  • Base Model: Qwen3-1.7B, a robust foundation for language tasks.
  • Fine-tuning Method: Utilizes the FRPO (Featherless Reinforcement Learning with Proximal Optimization) approach within the KL-in-LLM-RL experiments.
  • Checkpoint Details: The repository contains the global_step_200 checkpoint, saved in fp32 safetensors format without post-processing.
  • Configuration Encoding: The specific run configuration, including parameters like a4_center-k1-cGroupBoth-clip0.2-mb4-eta100-bs256x5-n2, is embedded directly in the model's name, providing transparency into its training setup.

Intended Use Cases

This model is primarily suited for:

  • RL Research: Experimenting with and analyzing the effects of different Reinforcement Learning fine-tuning strategies on LLMs.
  • Comparative Studies: Evaluating the performance and characteristics of FRPO-tuned models against other RL methods or base models.
  • Understanding RL Parameters: Investigating how specific RL configuration parameters (e.g., clip0.2, mb4, eta100) influence model behavior and capabilities.

Finetunes
1 models