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

Libraries

How to use huggingtweets/protoneutype with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use huggingtweets/protoneutype with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/protoneutype

SGLang

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

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

boris commited on Mar 24, 2021

Commit

1051368

1 Parent(s): f340165

New model from https://wandb.ai/wandb/huggingtweets/runs/7z0k8qgo

Browse files

Files changed (3) hide show

README.md +6 -6
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/protoneutype/1616622679794/predictions.png
 tags:
 - huggingtweets
 widget:
@@ -33,19 +33,19 @@ The model was trained on [@protoneutype's tweets](https://twitter.com/protoneuty
 | Data | Quantity |
 | --- | --- |
 | Tweets downloaded | 3223 |
-| Retweets | 720 |
 | Short tweets | 129 |
-| Tweets kept | 2374 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/31bddi5q/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 @protoneutype's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/2h7p7vx8) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/2h7p7vx8/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:
 | Data | Quantity |
 | --- | --- |
 | Tweets downloaded | 3223 |
+| Retweets | 719 |
 | Short tweets | 129 |
+| Tweets kept | 2375 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/2xz1sz9l/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 @protoneutype's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/7z0k8qgo) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/7z0k8qgo/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:ce07ee135a0111f04b7e27aa191026c2e52787f2afb56016c370158381c36094
 size 510408315

 version https://git-lfs.github.com/spec/v1
+oid sha256:e26b4d9c4168023009fff4d76632f0ca813a1c4a9f2ad3cb97b3c3de91f2ca95
 size 510408315

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49391119411e2a230f4fc0ed25d6c670ddf633ad6658107b792235ee50464c55
 size 2287

 version https://git-lfs.github.com/spec/v1
+oid sha256:5064b9f8449351d6c10b386bdb1fa2abdbd422629a367045935266a722c9df5d
 size 2287