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

Libraries

How to use huggingtweets/emailoctopus with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/emailoctopus with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/emailoctopus

SGLang

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

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

boris commited on Jan 1, 2021

Commit

e1a3841

1 Parent(s): ef86119

New model from https://wandb.ai/wandb/huggingtweets/runs/2ck1y5c1

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: https://www.huggingtweets.com/emailoctopus/1609534359805/predictions.png
 tags:
 - huggingtweets
 widget:
@@ -68,15 +68,15 @@ The model was trained on [@emailoctopus's tweets](https://twitter.com/emailoctop
 </tbody>
 </table>
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2a8qphhb/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 @emailoctopus's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2hcvegwk) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2hcvegwk/artifacts) is logged and versioned.
 ## Intended uses & limitations

 ---
 language: en
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
 </tbody>
 </table>
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/f7k5lmmf/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 @emailoctopus's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2ck1y5c1) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2ck1y5c1/artifacts) is logged and versioned.
 ## Intended uses & limitations

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe2e30fcb5406b98d0254d5733dece1f8c85e1353930e0fa3cbf9ad4ccc8b6c
 size 510406560

 version https://git-lfs.github.com/spec/v1
+oid sha256:6d361f5c710608b6844bea01f728fbb4fe3b3b1aa7289af7baf4ab92bda58b63
 size 510406560

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8771caa906dc254657ec88c12b1d10acc94affca6a10ee4684f178579ed6073
 size 1839

 version https://git-lfs.github.com/spec/v1
+oid sha256:be0998ce38656427e92386194d99a5b1d7081408c2ea991041dd36321f1d1f76
 size 1839