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

Libraries

How to use TextCortex/product_description_generator with Transformers:

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

pipe = pipeline("text-generation", model="TextCortex/product_description_generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TextCortex/product_description_generator")
model = AutoModelForCausalLM.from_pretrained("TextCortex/product_description_generator", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TextCortex/product_description_generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TextCortex/product_description_generator

SGLang

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

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

cderinbogaz commited on Jun 26, 2022

Commit

db26375

1 Parent(s): 1c0ffdb

Update README.md

Browse files

Files changed (1) hide show

README.md +17 -0

README.md CHANGED Viewed

@@ -1,3 +1,20 @@
 ---
 license: mit
 ---

 ---
 license: mit
 ---
+## TextCortex AI - Product Description Generator - Electronics Model
+This is one of our legacy models that was used for generating product descriptions for Electronic products. Because of the inference times, we trained this model on a very small version of the GPT-NEO with 125M parameters.
+Due to its small size, we had to train a model for each product category for our users.\
+We will be releasing other trained models on other categories soon.
+### How to Prompt:
+Just give your product name and add 'Product Description:' at the end of it to generate product descriptions.\
+Here is an example prompt:\
+`Product name: USB Dongle for video capture Product Description:`
+### TextCortex API
+If you want to generate product descriptions programatically, you can check out our API, hemingwAI at this link: https://textcortex.com/documentation/api