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

Libraries

How to use huggingtweets/amityexploder with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use huggingtweets/amityexploder with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/amityexploder

SGLang

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

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

boris commited on Jul 15, 2022

Commit

7789ba5

1 Parent(s): 0bfe94c

New model from https://wandb.ai/wandb/huggingtweets/runs/rcycu202

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/amityexploder/1657897958029/predictions.png
 tags:
 - huggingtweets
 widget:
@@ -47,15 +47,15 @@ The model was trained on tweets from SOPPY.
 | Short tweets | 574 |
 | Tweets kept | 2156 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2ycuys3d/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 @amityexploder's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2lnsy2bc) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2lnsy2bc/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 | 574 |
 | Tweets kept | 2156 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/16wq3mtu/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 @amityexploder's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/rcycu202) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/rcycu202/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:f70f2ad154513895891bb3c7f2b2a8f2cbecf1c574924d440b94f1ecf1eab2f4
 size 510396521

 version https://git-lfs.github.com/spec/v1
+oid sha256:7a175e0d50c8158a65b295ac32f3975c01cbe8a745daa956d2889f5aa8032125
 size 510396521

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f671b32dc50296695c1ca2dd091982ec2b246b9c9001c354db768662a9759a
 size 3311

 version https://git-lfs.github.com/spec/v1
+oid sha256:24add514fafe24c28be49a3870d770acfe2302128a3cf77cd9021a978f83a81a
 size 3311