Downloads · 30 days
5
8% of all-time downloads
sastpg/aaai27-alfworld-qwen3-4b-solver-v1
aaai27-alfworld-qwen3-4b-solver-v1 is a text generation model from sastpg. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Frozen ALFWorld plain-reasoning Solver baseline.
Downloads · 30 days
5
8% of all-time downloads
All-time downloads
63
Public
Parameters
4.4B
8.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors8.8 GB · 100%
From the Hugging Face model README
Frozen ALFWorld plain-reasoning Solver baseline.
This private artifact is an internal frozen Solver checkpoint for the AAAI 2027 test-time experience learning study. It contains model and tokenizer files only; training, reward, validation, and held-out task data are not included.
The checkpoint must be used with the environment-specific frozen prompt and evaluation protocol recorded in the project experiment manifest.