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

Libraries

How to use huggingtweets/weights_biases with Transformers:

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

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingtweets/weights_biases with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingtweets/weights_biases

SGLang

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

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

system HF Staff commited on Sep 17, 2020

Commit

5ccf631

1 Parent(s): fbe57ed

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -8

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 ---
 language: en
-thumbnail: http://res.cloudinary.com/huggingtweets/image/upload/v1599874469/weights_biases.jpg
 tags:
 - huggingtweets
 widget:
@@ -51,11 +51,11 @@ The model was trained on [@weights_biases's tweets](https://twitter.com/weights_
 <tbody style='border-width:0'>
 <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
 <td style='border-width:0'>Tweets downloaded</td>
-<td style='border-width:0'>956</td>
 </tr>
 <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
 <td style='border-width:0'>Retweets</td>
-<td style='border-width:0'>431</td>
 </tr>
 <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
 <td style='border-width:0'>Short tweets</td>
@@ -63,20 +63,20 @@ The model was trained on [@weights_biases's tweets](https://twitter.com/weights_
 </tr>
 <tr style='border-width:0'>
 <td style='border-width:0'>Tweets kept</td>
-<td style='border-width:0'>515</td>
 </tr>
 </tbody>
 </table>
-[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/2l6rpd2c/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 @weights_biases's tweets.
-Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/105hklom) for full transparency and reproducibility.
-At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/105hklom/artifacts) is logged and versioned.
 ## Intended uses & limitations
@@ -102,7 +102,7 @@ In addition, the data present in the user's tweets further affects the text gene
 </section>
-[![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/borisdayma)
 <section class='prose'>
 For more details, visit the project repository.

 ---
 language: en
+thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
 tags:
 - huggingtweets
 widget:
 <tbody style='border-width:0'>
 <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
 <td style='border-width:0'>Tweets downloaded</td>
+<td style='border-width:0'>975</td>
 </tr>
 <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
 <td style='border-width:0'>Retweets</td>
+<td style='border-width:0'>440</td>
 </tr>
 <tr style='border-width:0 0 1px 0; border-color: #E2E8F0'>
 <td style='border-width:0'>Short tweets</td>
 </tr>
 <tr style='border-width:0'>
 <td style='border-width:0'>Tweets kept</td>
+<td style='border-width:0'>525</td>
 </tr>
 </tbody>
 </table>
+[Explore the data](https://app.wandb.ai/wandb/huggingtweets/runs/15xg2sy0/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 @weights_biases's tweets.
+Hyperparameters and metrics are recorded in the [W&B training run](https://app.wandb.ai/wandb/huggingtweets/runs/3iv6bgks) for full transparency and reproducibility.
+At the end of training, [the final model](https://app.wandb.ai/wandb/huggingtweets/runs/3iv6bgks/artifacts) is logged and versioned.
 ## Intended uses & limitations
 </section>
+[![Follow](https://img.shields.io/twitter/follow/borisdayma?style=social)](https://twitter.com/intent/follow?screen_name=borisdayma)
 <section class='prose'>
 For more details, visit the project repository.