Overview

This model, DCAgent/a1-agenttuning_db, is an 8 billion parameter language model based on the Qwen3-8B architecture. It has been fine-tuned using a specialized dataset, /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--neulab-agenttuning-db-sandboxes_glm_4.7_traces_jupiter/snapshots/29b127789e036b60ccc377260480e9b67879a1a1_thinking_preprocessed, which consists of agent traces.

Key Capabilities

• Agent-tuned performance: Optimized for tasks related to AI agents, likely involving planning, reasoning, and interaction within defined environments.
• Qwen3-8B foundation: Benefits from the strong base capabilities of the Qwen3-8B model.

Training Details

The model was trained with a learning rate of 4e-05, a total batch size of 16, and utilized the ADAMW_TORCH_FUSED optimizer. Training spanned 7 epochs with a cosine learning rate scheduler and a warmup ratio of 0.1. The training environment included Transformers 4.57.6 and Pytorch 2.9.1+cu130.