Instructions to use Intel/fid_flan_t5_base_nq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/fid_flan_t5_base_nq with Transformers:

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

pipe = pipeline("text-generation", model="Intel/fid_flan_t5_base_nq")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Intel/fid_flan_t5_base_nq")
model = AutoModelForSeq2SeqLM.from_pretrained("Intel/fid_flan_t5_base_nq", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Intel/fid_flan_t5_base_nq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Intel/fid_flan_t5_base_nq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intel/fid_flan_t5_base_nq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Intel/fid_flan_t5_base_nq

SGLang

How to use Intel/fid_flan_t5_base_nq 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 "Intel/fid_flan_t5_base_nq" \
    --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": "Intel/fid_flan_t5_base_nq",
		"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 "Intel/fid_flan_t5_base_nq" \
        --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": "Intel/fid_flan_t5_base_nq",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Intel/fid_flan_t5_base_nq with Docker Model Runner:
```
docker model run hf.co/Intel/fid_flan_t5_base_nq
```

Fusion-In-Decoder Base on Natural Questions

This trained model is based on the Fusion-In-Decoder model, and trained on the Natural Questions dataset.

Model Details

Model is based on Fusion-In-Decoder, which in turn is based on the google/flan-t5-base checkpoint as the base model. For training, we utilized text retrieval for each query, which provides a collection of relevant passages for it.

We note that the passages were retrieved using a corpus based on Wikipedia.

Evaluation

See model performance on Evaluation Results tab on the right side.

Downloads last month: 139

Safetensors

Model size

0.2B params

Tensor type

BF16

Dataset used to train Intel/fid_flan_t5_base_nq

Paper for Intel/fid_flan_t5_base_nq

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Paper • 2007.01282 • Published Jul 2, 2020

Evaluation results

Exact Macth on NQ KILT
self-reported

51.550