energy-exp1-dpo-offline

CEIA-RL/energy-exp1-dpo-offline

Text Generation4B parameterstransformers
Tracked by OpenModelStats since September 22, 2026View on Hugging Face ↗
Downloads 30D
120
Total downloads
495
Gained 7D
—
Gained 30D
—
Likes
6
Rank · tracked models
—
–this week
Parameters
4B
Last source update
May 31, 2026

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-22. Charts appear as daily observations accumulate.

Overview

energy-exp1-dpo-offline is a text generation model published by CEIA-RL. OpenModelStats has tracked the model since Sep 22, 2026, most recently observing it 4h ago.

Published
May 30, 2026
Last updated
May 31, 2026
Library
transformers
License
—
Task
Text Generation
Parameters
4,022,468,096
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsqwen3text-generationgenerated_from_trainertrldpoconversationalarxiv:2305.18290base_model:CEIA-RL/qwen3-4b-dw-lr-GRPObase_model:finetune:CEIA-RL/qwen3-4b-dw-lr-GRPOtext-generation-inference

Publisher

CEIA-RLView publisher statistics →

Derived from CEIA-RL/qwen3-4b-dw-lr-GRPO (reported by the source; parent not yet tracked).

Similar models

Models similar to energy-exp1-dpo-offline
ModelDL 30D
Qwen3-4BQwen12.2M
Qwen3-4B-Instruct-2507Qwen3.5M
Qwen3-4B-Thinking-2507Qwen601.1K
Qwen3-4B-BaseQwen576K
Qwen3-4B-AWQQwen219.4K
qwen3-4b-base-dapo-v4ReliquaryForge139.8K