Instructions to use RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits with Transformers:

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

pipe = pipeline("text-generation", model="RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits

SGLang

How to use RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits 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 "RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits" \
    --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": "RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits",
		"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 "RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits" \
        --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": "RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/deepset_-_roberta-base-squad2-covid-8bits
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

roberta-base-squad2-covid - bnb 8bits

Model creator: https://huggingface.co/deepset/
Original model: https://huggingface.co/deepset/roberta-base-squad2-covid/

Original model description:

language: en datasets: - squad_v2 license: cc-by-4.0

roberta-base-squad2 for QA on COVID-19

Overview

Language model: deepset/roberta-base-squad2
Language: English
Downstream-task: Extractive QA
Training data: SQuAD-style CORD-19 annotations from 23rd April
Code: See an example QA pipeline on Haystack
Infrastructure: Tesla v100

Hyperparameters

batch_size = 24
n_epochs = 3
base_LM_model = "deepset/roberta-base-squad2"
max_seq_len = 384
learning_rate = 3e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.1
doc_stride = 128
xval_folds = 5
dev_split = 0
no_ans_boost = -100

license: cc-by-4.0

Performance

5-fold cross-validation on the data set led to the following results:

Single EM-Scores: [0.222, 0.123, 0.234, 0.159, 0.158]
Single F1-Scores: [0.476, 0.493, 0.599, 0.461, 0.465]
Single top\_3\_recall Scores: [0.827, 0.776, 0.860, 0.771, 0.777]
XVAL EM: 0.17890995260663506
XVAL f1: 0.49925444207319924
XVAL top\_3\_recall: 0.8021327014218009

This model is the model obtained from the third fold of the cross-validation.

Usage

In Haystack

For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in haystack:

reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2-covid")
# or 
reader = TransformersReader(model="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2-covid")

In Transformers

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline


model_name = "deepset/roberta-base-squad2-covid"

# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
    'question': 'Why is model conversion important?',
    'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)

# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

Authors

Branden Chan: branden.chan@deepset.ai
Timo Möller: timo.moeller@deepset.ai
Malte Pietsch: malte.pietsch@deepset.ai
Tanay Soni: tanay.soni@deepset.ai
Bogdan Kostić: bogdan.kostic@deepset.ai

About us

deepset is the company behind the open-source NLP framework Haystack which is designed to help you build production ready NLP systems that use: Question answering, summarization, ranking etc.

Some of our other work:

Get in touch and join the Haystack community

For more info on Haystack, visit our GitHub repo and Documentation.

We also have a Discord community open to everyone!

Twitter | LinkedIn | Discord | GitHub Discussions | Website

By the way: we're hiring!

Downloads last month: 3

Safetensors

Model size

0.1B params

Tensor type

F32

F16