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

Libraries

How to use huggingtweets/welcomeunknown with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huggingtweets/welcomeunknown")
model = AutoModelForCausalLM.from_pretrained("huggingtweets/welcomeunknown", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/welcomeunknown with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/welcomeunknown

SGLang

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

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

boris commited on May 20, 2022

Commit

f00a102

1 Parent(s): 76c25f0

New model from https://wandb.ai/wandb/huggingtweets/runs/1zq33izx

Browse files

Files changed (3) hide show

README.md +4 -4
pytorch_model.bin +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: http://www.huggingtweets.com/welcomeunknown/1653042803542/predictions.png
 tags:
 - huggingtweets
 widget:
@@ -47,15 +47,15 @@ The model was trained on tweets from b e a r 🤍⃤.
 | Short tweets | 214 |
 | Tweets kept | 1669 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/dcuusdvy/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 @welcomeunknown's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1kp9ij3h) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1kp9ij3h/artifacts) is logged and versioned.
 ## How to use

 ---
 language: en
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
 | Short tweets | 214 |
 | Tweets kept | 1669 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3jpmuox5/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 @welcomeunknown's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1zq33izx) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1zq33izx/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:ae2d48d141e40c4153a17590ca6071e4e1ace600e0d2cc75ece582f2cf3c4190
 size 510396521

 version https://git-lfs.github.com/spec/v1
+oid sha256:27c1f8e81a35790d45f70b007198d2d2d6ffef1a319b23f37e74fb270d903ebf
 size 510396521

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5be30da4966caf018579b0c38c4eea5e2a95393c5365003504516d384bc25d
 size 3247

 version https://git-lfs.github.com/spec/v1
+oid sha256:20a06994c4fd0e8c7ab089518a04fae917b6432ab3032f8b8161aa3b86d4b196
 size 3247