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

Libraries

How to use huggingtweets/deontologistics with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/deontologistics with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/deontologistics

SGLang

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

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

boris commited on Mar 25, 2021

Commit

8bcff15

1 Parent(s): 8e3df49

New model from https://wandb.ai/wandb/huggingtweets/runs/2dpgq6x6

Browse files

Files changed (3) hide show

README.md +3 -3
pytorch_model.bin +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -37,15 +37,15 @@ The model was trained on [@deontologistics's tweets](https://twitter.com/deontol
 | Short tweets | 187 |
 | Tweets kept | 2453 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/1qgq35hj/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 @deontologistics's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3o3h46g1) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3o3h46g1/artifacts) is logged and versioned.
 ## How to use

 | Short tweets | 187 |
 | Tweets kept | 2453 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3ahwv4uv/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 @deontologistics's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2dpgq6x6) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2dpgq6x6/artifacts) is logged and versioned.
 ## How to use

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50bbb021af9cfb500c2ebfded6f0df936a4eecb77334840566124e8f9c9b0ddb
 size 510408315

 version https://git-lfs.github.com/spec/v1
+oid sha256:bd6ed387a81dda4acf76ddb9d56108fdae5431fc55f2871fa33f446893b1a333
 size 510408315

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d247919b554dc8d30fb9053776a723c8d40aa240cc28b1c4b6d814e859596221
 size 2287

 version https://git-lfs.github.com/spec/v1
+oid sha256:102ce2a47017dd2e75291e19511b1a4fd07e51a36345a3e15d2681a6844a91b9
 size 2287