Instructions to use postbot/distilgpt2-emailgen-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use postbot/distilgpt2-emailgen-V2 with Transformers:

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

pipe = pipeline("text-generation", model="postbot/distilgpt2-emailgen-V2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("postbot/distilgpt2-emailgen-V2")
model = AutoModelForCausalLM.from_pretrained("postbot/distilgpt2-emailgen-V2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use postbot/distilgpt2-emailgen-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "postbot/distilgpt2-emailgen-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "postbot/distilgpt2-emailgen-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/postbot/distilgpt2-emailgen-V2

SGLang

How to use postbot/distilgpt2-emailgen-V2 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 "postbot/distilgpt2-emailgen-V2" \
    --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": "postbot/distilgpt2-emailgen-V2",
		"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 "postbot/distilgpt2-emailgen-V2" \
        --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": "postbot/distilgpt2-emailgen-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use postbot/distilgpt2-emailgen-V2 with Docker Model Runner:
```
docker model run hf.co/postbot/distilgpt2-emailgen-V2
```

pszemraj commited on Oct 1, 2022

Commit

06b3210

1 Parent(s): 218a890

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -50,6 +50,8 @@ parameters:
 > This is a V2, which should perform better than V1. This is in the process of being evaluated.
 Why write the rest of your email when you can generate it?
 ```python
@@ -75,8 +77,6 @@ result = generator(
 print(result[0]['generated_text'])
 ```
-**[colab notebook](https://colab.research.google.com/gist/pszemraj/d1c2d88b6120cca4ca7df078ea1d1e50/scratchpad.ipynb)**
 ## Model description
 This model is a fine-tuned version of `distilgpt2` on the postbot/multi-emails-100k dataset.

 > This is a V2, which should perform better than V1. This is in the process of being evaluated.
+[![colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/pszemraj/d1c2d88b6120cca4ca7df078ea1d1e50/scratchpad.ipynb)
 Why write the rest of your email when you can generate it?
 ```python
 print(result[0]['generated_text'])
 ```
 ## Model description
 This model is a fine-tuned version of `distilgpt2` on the postbot/multi-emails-100k dataset.