IDEALLab
/

Qwen2.5-Coder-14B-Instruct-GRPO-SDS-Ablation-Prompt-seed303

Reinforcement Learning

text-generation

combinatorial-optimization

code-generation

text-generation-inference

Model card Files Files and versions

Qwen2.5-Coder-14B-Instruct-GRPO-SDS-Ablation-Prompt-seed303

Description

Prompt ablation (seed 303).

This model is part of the Neural Solver Synthesis project (ICML 2026). It acts as a compiled solver for the SDS problem.

Artifacts

Training Data: SoheylM/OpenR1-SDS-10k-seed303
Base Model: Qwen 2.5 Coder 14B

Downloads last month: 14

Safetensors

Model size

15B params

Tensor type

BF16

·

Video Preview

Reinforcement Learning

loading

Model tree for IDEALLab/Qwen2.5-Coder-14B-Instruct-GRPO-SDS-Ablation-Prompt-seed303

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-Coder-14B

Finetuned

Qwen/Qwen2.5-Coder-14B-Instruct

Finetuned

(105)

this model

Collection including IDEALLab/Qwen2.5-Coder-14B-Instruct-GRPO-SDS-Ablation-Prompt-seed303

Neural Solver Synthesis

Official artifacts for Neural Solver Synthesis: SDS data, solver checkpoints, revision bundles, and JSSP transfer artifacts. • 48 items • Updated 3 days ago