---
base_model: Qwen/Qwen2.5-7B-Instruct
base_model_relation: finetune
library_name: transformers
pipeline_tag: text-generation
license: apache-2.0
tags:
  - evoke
  - alfworld
  - agent
  - arxiv:2609.38334
---

# 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](https://arxiv.org/abs/2609.38334) · [Code and evaluation](https://github.com/Gnonymous/EVOKE) · [Project page](https://gnonymous.github.io/EVOKE)

## Load

```python
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](https://github.com/Gnonymous/EVOKE), then run:

```bash
.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.