Instructions to use AL-GR/Forge-Qwen2.5-0.5B-s1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AL-GR/Forge-Qwen2.5-0.5B-s1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AL-GR/Forge-Qwen2.5-0.5B-s1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AL-GR/Forge-Qwen2.5-0.5B-s1")
model = AutoModelForCausalLM.from_pretrained("AL-GR/Forge-Qwen2.5-0.5B-s1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AL-GR/Forge-Qwen2.5-0.5B-s1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AL-GR/Forge-Qwen2.5-0.5B-s1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AL-GR/Forge-Qwen2.5-0.5B-s1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AL-GR/Forge-Qwen2.5-0.5B-s1

SGLang

How to use AL-GR/Forge-Qwen2.5-0.5B-s1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AL-GR/Forge-Qwen2.5-0.5B-s1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AL-GR/Forge-Qwen2.5-0.5B-s1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AL-GR/Forge-Qwen2.5-0.5B-s1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AL-GR/Forge-Qwen2.5-0.5B-s1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AL-GR/Forge-Qwen2.5-0.5B-s1 with Docker Model Runner:
```
docker model run hf.co/AL-GR/Forge-Qwen2.5-0.5B-s1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)

Forge-Qwen2.5-0.5B-s1

This model is initialized from the pre-trained Qwen/Qwen2.5-0.5B and fine-tuned on the AL-GR/AL-GR-v1 dataset using the FORGE framework for 1 epoch.

It is presented in the paper FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets.

GitHub Repository: https://github.com/selous123/al_sid
Project Page: https://huggingface.co/AL-GR

Evaluation Results on AL-GR/AL-GR-v1

Model	HR@20	HR@100	HR@500	HR@1000
Forge-Qwen 2.5-0.5B-Base-s1	0.0506	0.1277	0.2602	0.3068
Forge-T5-Base-s1	0.0284	0.0689	0.1372	0.1557

Note: HR@K denotes Hit Rate at K — the proportion of test queries for which the correct answer appears in the top-K retrieved/generated results.

Usage

1. Download the Model

You can download this model locally using the huggingface_hub library:

import os
os.environ["HF_ENDPOINT"] = "https://hf-mirror.com" # Optional: use mirror for faster download in some regions
os.environ["KMP_DUPLICATE_LIB_OK"] = "True"

from huggingface_hub import snapshot_download

snapshot_download(
repo_id='AL-GR/Forge-Qwen2.5-0.5B-s1',
local_dir='{YOUR_LOCAL_DIR}', # Replace with your desired local path
local_dir_use_symlinks=False,
)

For more details about the training setup, dataset, or evaluation protocol, please refer to the FORGE framework repository.

Citation

@article{fu2025forge,
  title={FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets},
  author={Fu, Kairui and Zhang, Tao and Xiao, Shuwen and Wang, Ziyang and Zhang, Xinming and Zhang, Chenchi and Yan, Yuliang and Zheng, Junjun and others},
  journal={arXiv preprint arXiv:2509.20904},
  year={2025}
}

Downloads last month: 76

Safetensors

Model size

0.6B params

Tensor type

F32

Model tree for AL-GR/Forge-Qwen2.5-0.5B-s1

Base model

Qwen/Qwen2.5-0.5B

Finetuned

(724)

this model

Quantizations

1 model

Dataset used to train AL-GR/Forge-Qwen2.5-0.5B-s1

Paper for AL-GR/Forge-Qwen2.5-0.5B-s1

FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets

Paper • 2509.20904 • Published Sep 25, 2025 • 3