EVOKE-ALFWorld-7B

EVOKE is a post-training method that elicits world knowledge for goal-directed decisions. This is the full model for ALFWorld, based on Qwen2.5-7B-Instruct.

Paper · Code and evaluation · Project page

Load

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Gnonymous/EVOKE-ALFWorld-7B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype="auto", device_map="auto"
)

ALFWorld evaluation

Follow the installation and data instructions in the GitHub repository, then run:

.venv/inference/bin/python evaluate_alfworld.py \
  --model Gnonymous/EVOKE-ALFWorld-7B \
  --data-root /path/to/alfworld/json_2.1.1 \
  --output /path/to/results/evoke-7b \
  --gpus 0

Built with Qwen. See the included LICENSE and NOTICE files.