Instructions to use huggingtweets/dulari_sister with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huggingtweets/dulari_sister with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="huggingtweets/dulari_sister")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("huggingtweets/dulari_sister") model = AutoModelForCausalLM.from_pretrained("huggingtweets/dulari_sister") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use huggingtweets/dulari_sister with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huggingtweets/dulari_sister" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huggingtweets/dulari_sister", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/huggingtweets/dulari_sister
- SGLang
How to use huggingtweets/dulari_sister 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/dulari_sister" \ --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/dulari_sister", "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/dulari_sister" \ --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/dulari_sister", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use huggingtweets/dulari_sister with Docker Model Runner:
docker model run hf.co/huggingtweets/dulari_sister
Update README.md
#2
by abdullah2021 - opened
README.md
CHANGED
|
@@ -1,85 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
language: en
|
| 3 |
-
thumbnail: http://www.huggingtweets.com/dulari_sister/1676026609811/predictions.png
|
| 4 |
-
tags:
|
| 5 |
-
- huggingtweets
|
| 6 |
widget:
|
| 7 |
-
- text:
|
| 8 |
-
---
|
| 9 |
-
|
| 10 |
-
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
| 11 |
-
<div class="flex">
|
| 12 |
-
<div
|
| 13 |
-
style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1614604068818931712/Nf9g-B08_400x400.jpg')">
|
| 14 |
-
</div>
|
| 15 |
-
<div
|
| 16 |
-
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
|
| 17 |
-
</div>
|
| 18 |
-
<div
|
| 19 |
-
style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('')">
|
| 20 |
-
</div>
|
| 21 |
-
</div>
|
| 22 |
-
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
|
| 23 |
-
<div style="text-align: center; font-size: 16px; font-weight: 800">❣️दुलारी बहन ❣️</div>
|
| 24 |
-
<div style="text-align: center; font-size: 14px;">@dulari_sister</div>
|
| 25 |
-
</div>
|
| 26 |
-
|
| 27 |
-
I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
|
| 28 |
-
|
| 29 |
-
Create your own bot based on your favorite user with [the demo](https://colab.research.google.com/github/borisdayma/huggingtweets/blob/master/huggingtweets-demo.ipynb)!
|
| 30 |
-
|
| 31 |
-
## How does it work?
|
| 32 |
-
|
| 33 |
-
The model uses the following pipeline.
|
| 34 |
-
|
| 35 |
-

|
| 36 |
-
|
| 37 |
-
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).
|
| 38 |
-
|
| 39 |
-
## Training data
|
| 40 |
-
|
| 41 |
-
The model was trained on tweets from ❣️दुलारी बहन ❣️.
|
| 42 |
-
|
| 43 |
-
| Data | ❣️दुलारी बहन ❣️ |
|
| 44 |
-
| --- | --- |
|
| 45 |
-
| Tweets downloaded | 1014 |
|
| 46 |
-
| Retweets | 84 |
|
| 47 |
-
| Short tweets | 165 |
|
| 48 |
-
| Tweets kept | 765 |
|
| 49 |
-
|
| 50 |
-
[Explore the data](https://wandb.ai/wandb/huggingtweets/runs/bdms052n/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
| 51 |
-
|
| 52 |
-
## Training procedure
|
| 53 |
-
|
| 54 |
-
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @dulari_sister's tweets.
|
| 55 |
-
|
| 56 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/ozoko36e) for full transparency and reproducibility.
|
| 57 |
-
|
| 58 |
-
At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/ozoko36e/artifacts) is logged and versioned.
|
| 59 |
-
|
| 60 |
-
## How to use
|
| 61 |
-
|
| 62 |
-
You can use this model directly with a pipeline for text generation:
|
| 63 |
-
|
| 64 |
-
```python
|
| 65 |
-
from transformers import pipeline
|
| 66 |
-
generator = pipeline('text-generation',
|
| 67 |
-
model='huggingtweets/dulari_sister')
|
| 68 |
-
generator("My dream is", num_return_sequences=5)
|
| 69 |
-
```
|
| 70 |
-
|
| 71 |
-
## Limitations and bias
|
| 72 |
-
|
| 73 |
-
The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
|
| 74 |
-
|
| 75 |
-
In addition, the data present in the user's tweets further affects the text generated by the model.
|
| 76 |
-
|
| 77 |
-
## About
|
| 78 |
-
|
| 79 |
-
*Built by Boris Dayma*
|
| 80 |
-
|
| 81 |
-
[](https://twitter.com/intent/follow?screen_name=borisdayma)
|
| 82 |
-
|
| 83 |
-
For more details, visit the project repository.
|
| 84 |
-
|
| 85 |
-
[](https://github.com/borisdayma/huggingtweets)
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
widget:
|
| 3 |
+
- text:
|
| 4 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|