47 lines
1.3 KiB
Markdown
47 lines
1.3 KiB
Markdown
|
---
|
||
|
|
base_model: Qwen/Qwen2.5-3B-Instruct
|
||
|
|
base_model_relation: finetune
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
license: other
|
||
|
|
license_name: qwen-research
|
||
|
|
license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
|
||
|
|
tags:
|
||
|
|
- evoke
|
||
|
|
- alfworld
|
||
|
|
- agent
|
||
|
|
- arxiv:2609.38334
|
||
|
|
---
|
||
|
|
|
||
|
|
# EVOKE-ALFWorld-3B
|
||
|
|
|
||
|
|
EVOKE is a post-training method that elicits world knowledge for goal-directed decisions. This is the full model for ALFWorld, based on Qwen2.5-3B-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-3B"
|
||
|
|
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-3B \
|
||
|
|
--data-root /path/to/alfworld/json_2.1.1 \
|
||
|
|
--output /path/to/results/evoke-3b \
|
||
|
|
--gpus 0
|
||
|
|
```
|
||
|
|
|
||
|
|
Built with Qwen. See the included LICENSE and NOTICE files.
|