Instructions to use kargaranamir/T5R-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kargaranamir/T5R-base with Transformers:

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

pipe = pipeline("text-generation", model="kargaranamir/T5R-base")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("kargaranamir/T5R-base")
model = AutoModelForSeq2SeqLM.from_pretrained("kargaranamir/T5R-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kargaranamir/T5R-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kargaranamir/T5R-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kargaranamir/T5R-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kargaranamir/T5R-base

SGLang

How to use kargaranamir/T5R-base 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 "kargaranamir/T5R-base" \
    --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": "kargaranamir/T5R-base",
		"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 "kargaranamir/T5R-base" \
        --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": "kargaranamir/T5R-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kargaranamir/T5R-base with Docker Model Runner:
```
docker model run hf.co/kargaranamir/T5R-base
```

kargaranamir commited on Aug 28, 2023

Commit

3d114da

1 Parent(s): 3e48fc2

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -45,11 +45,11 @@ You can use the `transformers` library to load and utilize the T5-Reverse (T5R)
 >>> # Example instruction and prompt
 >>> sample = '''
-Instruction: X
-Output: 1- Base your meals on higher fibre starchy carbohydrates. 2- Eat lots of fruit and veg. 3- Eat more fish, including a portion of oily fish.
-What kind of instruction could this be the answer to?
-X:
-'''
 >>> # Generate a response using the model
 >>> res = inference(sample)

 >>> # Example instruction and prompt
 >>> sample = '''
+>>> Instruction: X
+>>> Output: 1- Base your meals on higher fibre starchy carbohydrates. 2- Eat lots of fruit and veg. 3- Eat more fish, including a portion of oily fish.
+>>> What kind of instruction could this be the answer to?
+>>> X:
+>>> '''
 >>> # Generate a response using the model
 >>> res = inference(sample)