This are models trained based on this paper. Pretrained on SlimPajama-6B and Fine-Tuned on SWE-smith trajectories by Claude 3.7 Sonnet. For more information see

code here
Paper, descriptions and metircs are here

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Kirili4ik/ICAE-for-SWE-agents

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

(1578)

this model

Datasets used to train Kirili4ik/ICAE-for-SWE-agents

Papers for Kirili4ik/ICAE-for-SWE-agents

On Problems of Implicit Context Compression for Software Engineering Agents

Paper • 2605.11051 • Published 4 days ago

In-context Autoencoder for Context Compression in a Large Language Model

Paper • 2307.06945 • Published Jul 13, 2023 • 29