u-10bei/sft_alfworld_trajectory_dataset_v5 download history
u-10bei/sft_alfworld_trajectory_dataset_v5 is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 62 times (18 in the last 7 days), and 7,277 times in total. It ranks #160,836 among datasets by monthly downloads.
ALFWorld Trajectory Dataset Overview This is a synthetic SFT (Supervised Fine-Tuning) dataset designed for agent training in ALFWorld-compatible environments. The dataset programmatically generates expert trajectories without requiring an actual ALFWorld environment or a large
Models trained on sft_alfworld_trajectory_dataset_v5
1,489 models list it as training data.
- moushi21/agent-bench-alfworld-merged3 39 downloads in 30 days
- deepkick/qwen3-4b-advanced-dpo-v21-merged 32 downloads in 30 days
- deepkick/qwen3-4b-advanced-sft-v0-merged 30 downloads in 30 days
- deepkick/qwen3-4b-advanced-dpo-v26-merged 27 downloads in 30 days
- deepkick/qwen3-4b-advanced-dpo-v27-merged 27 downloads in 30 days
- Kaito-F/qwen3-4b-grpo-v3 26 downloads in 30 days
- ShogoMu/qwen25_7b_lora_agentbench_v6 26 downloads in 30 days
- deepkick/qwen3-4b-advanced-dpo-v20-merged 25 downloads in 30 days
- choco800/qwen3-4b-agent-v16 25 downloads in 30 days
- deepkick/qwen25-7b-advanced-sft-v0-merged 24 downloads in 30 days
- deepkick/qwen3-4b-advanced-sft-v08-merged 23 downloads in 30 days
- deepkick/qwen3-4b-advanced-sft-v16-merged 23 downloads in 30 days
Open u-10bei/sft_alfworld_trajectory_dataset_v5 on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.