Instructions to use assafbk/decimamba-130m-squad-doc-ret with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use assafbk/decimamba-130m-squad-doc-ret with Transformers:

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

pipe = pipeline("text-generation", model="assafbk/decimamba-130m-squad-doc-ret")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("assafbk/decimamba-130m-squad-doc-ret", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use assafbk/decimamba-130m-squad-doc-ret with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "assafbk/decimamba-130m-squad-doc-ret"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "assafbk/decimamba-130m-squad-doc-ret",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/assafbk/decimamba-130m-squad-doc-ret

SGLang

How to use assafbk/decimamba-130m-squad-doc-ret 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 "assafbk/decimamba-130m-squad-doc-ret" \
    --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": "assafbk/decimamba-130m-squad-doc-ret",
		"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 "assafbk/decimamba-130m-squad-doc-ret" \
        --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": "assafbk/decimamba-130m-squad-doc-ret",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use assafbk/decimamba-130m-squad-doc-ret with Docker Model Runner:
```
docker model run hf.co/assafbk/decimamba-130m-squad-doc-ret
```

DeciMamba Checkpoint

The official checkpoint of DeciMamba-130m, finetuned for the Document Retrieval task as presented in DeciMamba: Exploring the Length Extrapolation Potential of Mamba.

See our Github Repo for evalution and training scripts.

Bibtex:

@misc{benkish2024decimambaexploringlengthextrapolation,
      title={DeciMamba: Exploring the Length Extrapolation Potential of Mamba}, 
      author={Assaf Ben-Kish and Itamar Zimerman and Shady Abu-Hussein and Nadav Cohen and Amir Globerson and Lior Wolf and Raja Giryes},
      year={2024},
      eprint={2406.14528},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2406.14528}, 
}

Downloads last month: 3

Paper for assafbk/decimamba-130m-squad-doc-ret

DeciMamba: Exploring the Length Extrapolation Potential of Mamba

Paper • 2406.14528 • Published Jun 20, 2024