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

Libraries

How to use PardisSzah/BasePersianTextFormalizer with Transformers:

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

pipe = pipeline("text-generation", model="PardisSzah/BasePersianTextFormalizer")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("PardisSzah/BasePersianTextFormalizer")
model = AutoModelForMultimodalLM.from_pretrained("PardisSzah/BasePersianTextFormalizer")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PardisSzah/BasePersianTextFormalizer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PardisSzah/BasePersianTextFormalizer

SGLang

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

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

PardisSzah commited on Feb 29, 2024

Commit

f0c3054

verified ·

1 Parent(s): eef8bb4

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -13,14 +13,13 @@ This model is fine-tuned to generate formal text from informal text based on the
 ## Usage
 ```python
-from transformers import  AutoModelForSeq2SeqLM, MT5Tokenizer
 model = T5ForConditionalGeneration.from_pretrained('PardisSzah/BasePersianTextFormalizer')
 tokenizer = AutoTokenizer.from_pretrained('PardisSzah/BasePersianTextFormalizer')
-from transformers import (T5ForConditionalGeneration, AutoTokenizer, pipeline)
-import torch
 pipe = pipeline(task='text2text-generation', model=model, tokenizer=tokenizer)
 def test_model(text):
   device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

 ## Usage
 ```python
+from transformers import (T5ForConditionalGeneration, AutoTokenizer, pipeline)
+import torch
 model = T5ForConditionalGeneration.from_pretrained('PardisSzah/BasePersianTextFormalizer')
 tokenizer = AutoTokenizer.from_pretrained('PardisSzah/BasePersianTextFormalizer')
 pipe = pipeline(task='text2text-generation', model=model, tokenizer=tokenizer)
 def test_model(text):
   device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')