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

Libraries

How to use miguelgargallo/huggingtweets with Transformers:

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

pipe = pipeline("text-generation", model="miguelgargallo/huggingtweets")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("miguelgargallo/huggingtweets")
model = AutoModelForCausalLM.from_pretrained("miguelgargallo/huggingtweets")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use miguelgargallo/huggingtweets with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/miguelgargallo/huggingtweets

SGLang

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

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

🚩 Report : Legal issue(s)

by miguelgargallo - opened Nov 1, 2022

Discussion

miguelgargallo

Owner Nov 1, 2022

•

edited Nov 1, 2022

Is there a way to make private? or Co author me? or transfer author¿?

boris

Nov 1, 2022

Yeah, let me do that now

boris

Nov 1, 2022

Hum actually I don't have access to it… maybe @julien-c can suggest how to transfer this model to you?

miguelgargallo

Owner Nov 1, 2022

Well, at least co-author, it's okay

miguelgargallo

Owner Nov 1, 2022

But transfer is okay too!

boris

Nov 1, 2022

Cannot do to 1 model only.
Maybe create an org, add me, then I can transfer it to that org, then you can transfer wherever you want (personal account).

Otherwise these are just git repos so maybe you can git clone and upload to your own repo (but may be difficult if you're not familiar with git).

elonmuskceo

Nov 1, 2022

hi @miguelgargallo I can transfer this model to your user account, would that work for you?

miguelgargallo

Owner Nov 1, 2022

Perfect! That sounds amazing!

julien-c

Nov 1, 2022

done:)

miguelgargallo

Owner Nov 1, 2022

Thanks <3 lovely! It's amazing and I will publish updates and cover on twitter any new advancement!

miguelgargallo changed discussion status to closed Nov 1, 2022

miguelgargallo

Owner Nov 1, 2022

To deliver credit, I flipped the name of the repo, from huggingtweets/miguelgargallo to miguelgargallo/huggingtweets! Thanks!

miguelgargallo changed discussion status to open Nov 1, 2022

miguelgargallo

Owner Nov 1, 2022

Have a nice week!

miguelgargallo changed discussion status to closed Nov 2, 2022

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment