FRPO/qwen3-1.7b-a7_current_kl-curKL-k1-cNone-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-a7_current_kl-curKL-k1-cNone-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) through the KL-in-LLM-RL / FRPO experimental framework. This model, developed within the FRPO experiments, focuses on RL-based optimization. It is provided as an fp32 safetensors checkpoint, suitable for researchers and developers exploring advanced RL fine-tuning techniques for large language models.

Loading preview...

Model Overview

This model, FRPO/qwen3-1.7b-a7_current_kl-curKL-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2, is a 2 billion parameter language model derived from the Qwen/Qwen3-1.7B base architecture. It represents a checkpoint from the KL-in-LLM-RL / FRPO experimental series, specifically fine-tuned using Reinforcement Learning (RL) with the verl framework.

Key Characteristics

  • Base Model: Qwen3-1.7B, indicating a robust foundation for language understanding and generation.
  • Fine-tuning Method: Utilizes Reinforcement Learning (RL) as part of the KL-in-LLM-RL / FRPO experiments, suggesting a focus on optimizing specific behaviors or performance metrics through iterative learning.
  • Checkpoint: The provided checkpoint is global_step_200, indicating a specific stage in the RL training process.
  • Weights Format: The model weights are in fp32 safetensors format, preserved exactly as saved by the trainer without further post-processing.
  • Configuration: The run configuration for this specific experimental variant is encoded directly within the repository name.

Intended Use Cases

This model is primarily intended for:

  • RL Research: Researchers and practitioners interested in the application and effects of Reinforcement Learning for fine-tuning large language models.
  • Experimental Analysis: Studying the outcomes and performance characteristics of models trained under the KL-in-LLM-RL / FRPO framework.
  • Comparative Studies: Evaluating the impact of specific RL configurations (like curKL-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2) on model behavior and capabilities.

Finetunes
1 models