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

Libraries

How to use huggingtweets/pauljwright with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use huggingtweets/pauljwright with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/pauljwright

SGLang

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

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

system HF Staff commited on Oct 10, 2020

Commit

47ea413

1 Parent(s): f4f23fe

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: https://www.huggingtweets.com/pauljwright/1602302560810/predictions.png
 tags:
 - huggingtweets
 widget:
@@ -68,15 +68,15 @@ The model was trained on [@pauljwright's tweets](https://twitter.com/pauljwright
 </tbody>
 </table>
-[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/1y8iq5a6/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @pauljwright's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/c99948ze) for full transparency and reproducibility.
-At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/c99948ze/artifacts) is logged and versioned.
 ## Intended uses & limitations
@@ -110,4 +110,4 @@ For more details, visit the project repository.
 [![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)
-<!--- random size file                                                 -->

 ---
 language: en
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
 </tbody>
 </table>
+[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/29953svy/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @pauljwright's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/2f1n460p) for full transparency and reproducibility.
+At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/2f1n460p/artifacts) is logged and versioned.
 ## Intended uses & limitations
 [![GitHub stars](https://img.shields.io/github/stars/borisdayma/huggingtweets?style=social)](https://github.com/borisdayma/huggingtweets)
+<!--- random size file                                        -->