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

Libraries

How to use huggingtweets/monodevice with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/monodevice with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/monodevice

SGLang

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

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

boris commited on Mar 26, 2021

Commit

2804975

1 Parent(s): 2b59411

New model from https://wandb.ai/wandb/huggingtweets/runs/grki2wea

Browse files

Files changed (3) hide show

README.md +7 -7
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/monodevice/1616644199866/predictions.png
 tags:
 - huggingtweets
 widget:
@@ -24,7 +24,7 @@ The model uses the following pipeline.
 ![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true)
-To understand how the model was developed, check the [W&B report](https://app.wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-model-to-generate-tweets--VmlldzoxMTY5MjI).
 ## Training data
@@ -34,18 +34,18 @@ The model was trained on [@monodevice's tweets](https://twitter.com/monodevice).
 | --- | --- |
 | Tweets downloaded | 3246 |
 | Retweets | 28 |
-| Short tweets | 984 |
-| Tweets kept | 2234 |
-[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3icqdn6s/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 @monodevice's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3s9nlykt) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3s9nlykt/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:
 ![pipeline](https://github.com/borisdayma/huggingtweets/blob/master/img/pipeline.png?raw=true)
+To understand how the model was developed, check the [W&B report](https://wandb.ai/wandb/huggingtweets/reports/HuggingTweets-Train-a-Model-to-Generate-Tweets--VmlldzoxMTY5MjI).
 ## Training data
 | --- | --- |
 | Tweets downloaded | 3246 |
 | Retweets | 28 |
+| Short tweets | 982 |
+| Tweets kept | 2236 |
+[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/x9k48ocy/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 @monodevice's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/grki2wea) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/grki2wea/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 sha256:0b681473f642a46851cc773bdbd5e09082e0bfef0851cbda3b6ecafc1d1e05ed
 size 510408315

 version https://git-lfs.github.com/spec/v1
+oid sha256:e733247db097fbd8cfc202df24d217e5719c1d8be3d14da623474c1f595a7db6
 size 510408315

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494ecd1722526365702520ea9fa129718423711e6fc7a2dc7dedc5be349ab1e8
 size 2287

 version https://git-lfs.github.com/spec/v1
+oid sha256:e6ac1e6a3e4bc7bc5f641a8852801a86c6be088824ad8017aae794ede35f095d
 size 2287