FRPO/qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed2

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-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed2 is a 2 billion parameter language model based on the Qwen3-1.7B architecture, developed by FRPO. This model is an RL fine-tuned checkpoint from the KL-in-LLM-RL / FRPO experiments, specifically trained using the verl framework. It is designed for research and experimentation in reinforcement learning applications for large language models.

Loading preview...

Model Overview

This model, FRPO/qwen3-1.7b-a1_base-k1-cNone-clip0.2-mb4-eta100-bs256x5-n2-seed2, 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, fine-tuned using Reinforcement Learning (RL) with the verl framework.

Key Characteristics

  • Base Model: Utilizes the Qwen3-1.7B as its foundation.
  • Fine-tuning Method: RL fine-tuned using the verl framework, indicating a focus on optimizing specific behaviors or objectives through reinforcement learning.
  • Checkpoint: The repository contains the global_step_200 checkpoint, saved in fp32 safetensors format without additional post-processing.
  • Configuration: The specific run configuration parameters are encoded directly within the model's repository name, providing transparency into its training setup.

Intended Use Cases

This model is primarily suited for:

  • RL Research: Experimentation and development in reinforcement learning applied to large language models.
  • Comparative Studies: Analyzing the effects of different RL fine-tuning strategies on Qwen3-1.7B.
  • Advanced LLM Development: Exploring how RL can enhance specific capabilities or mitigate limitations of base language models.

Finetunes
1 models