Instructions to use PeterBrendan/Prebid_Module_GPT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PeterBrendan/Prebid_Module_GPT2 with Transformers:

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

pipe = pipeline("text-generation", model="PeterBrendan/Prebid_Module_GPT2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PeterBrendan/Prebid_Module_GPT2")
model = AutoModelForCausalLM.from_pretrained("PeterBrendan/Prebid_Module_GPT2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PeterBrendan/Prebid_Module_GPT2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PeterBrendan/Prebid_Module_GPT2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PeterBrendan/Prebid_Module_GPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PeterBrendan/Prebid_Module_GPT2

SGLang

How to use PeterBrendan/Prebid_Module_GPT2 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 "PeterBrendan/Prebid_Module_GPT2" \
    --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": "PeterBrendan/Prebid_Module_GPT2",
		"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 "PeterBrendan/Prebid_Module_GPT2" \
        --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": "PeterBrendan/Prebid_Module_GPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PeterBrendan/Prebid_Module_GPT2 with Docker Model Runner:
```
docker model run hf.co/PeterBrendan/Prebid_Module_GPT2
```

PeterBrendan commited on Jul 20, 2023

Commit

31ea32e

1 Parent(s): 5a2abda

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -10,13 +10,13 @@ widget:
 **Model name:** Prebid_Module_GPT2
-**Model description:** This fine-tuned version of the GPT-2 model was trained on a dataset of 1100+ publisher domains' Prebid installed modules. It aims to provide insights into what Prebid modules other publishers install with their Prebid set-up. Given a Prebid module, such as ***'appnexusBidAdapter'***, the model can generate a sample Prebid installed Prebid modules based on the collected data. It helps publishers gain an understanding of how different publishers use Prebid modules.
 **Intended uses:** This model is intended to assist publishers in understanding and exploring how other publishers use Prebid modules. It serves as a reference to gain insights into common configurations, best practices, and different approaches used by publishers across various domains.
 **Limitations:** It's important to note that the generated installed Prebid modules are based on the data from the training set and may not cover all possible combinations or reflect the specific requirements of a particular domain. Publishers should carefully review and adapt the generated installed Prebid modules to their specific needs and business rules.
-**How to use:** To use this model, provide a Prebid module, such as ***'gptPreAuction',***. The model will generate a sample Prebid installed modules combination related to that input based on the collected data from that point forward. To start from the beginning, use **[** as the input.
 **Training data:** This model was trained on a dataset consisting of over 1100+ publisher domains Prebid modules. The dataset was collected from a variety of publishers and represents a wide range of Prebid settings used in the industry.

 **Model name:** Prebid_Module_GPT2
+**Model description:** This fine-tuned version of the GPT-2 model was trained on a dataset of 1100+ publisher domains' Prebid installed modules. The model aims to provide insights into what Prebid modules other publishers install with their Prebid set-up. Given a Prebid module, such as ***appnexusBidAdapter***, the model can generate a sample Prebid installed modules combination based on the collected data. This helps publishers gain an understanding of how different publishers use Prebid modules.
 **Intended uses:** This model is intended to assist publishers in understanding and exploring how other publishers use Prebid modules. It serves as a reference to gain insights into common configurations, best practices, and different approaches used by publishers across various domains.
 **Limitations:** It's important to note that the generated installed Prebid modules are based on the data from the training set and may not cover all possible combinations or reflect the specific requirements of a particular domain. Publishers should carefully review and adapt the generated installed Prebid modules to their specific needs and business rules.
+**How to use:** To use this model, provide a Prebid module, such as ***gptPreAuction***. The model will generate a sample Prebid installed modules combination related to that input based on the collected data from that point forward. To start from the beginning, use ***[*** as the input.
 **Training data:** This model was trained on a dataset consisting of over 1100+ publisher domains Prebid modules. The dataset was collected from a variety of publishers and represents a wide range of Prebid settings used in the industry.