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

Libraries

How to use abagade/IndianPoliticalTweetsLM with Transformers:

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

pipe = pipeline("text-generation", model="abagade/IndianPoliticalTweetsLM")

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

tokenizer = AutoTokenizer.from_pretrained("abagade/IndianPoliticalTweetsLM")
model = AutoModelForCausalLM.from_pretrained("abagade/IndianPoliticalTweetsLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abagade/IndianPoliticalTweetsLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/abagade/IndianPoliticalTweetsLM

SGLang

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

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

system HF Staff commited on Sep 10, 2020

Commit

d9489ca

1 Parent(s): 55de5e7

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -22,6 +22,7 @@ datasets:
 Indian Political Tweets LM
 ## Model description
 This is a GPT2 Language model with LM head fine-tuned on tweets crawled from handles which belong predominantly to Indian Politics. For more information about the crawled data, you can go through this [blog](https://bagdeabhishek.github.io/twitterAnalysis) post.

 Indian Political Tweets LM
 ## Model description
+Note: This model is based on GPT2, if you want a bigger model based on GPT2-medium and finetuned on the same data please take a look at the [IndianPoliticalTweetsLMMedium](https://huggingface.co/bagdaebhishek/IndianPoliticalTweetsLMMedium) model.
 This is a GPT2 Language model with LM head fine-tuned on tweets crawled from handles which belong predominantly to Indian Politics. For more information about the crawled data, you can go through this [blog](https://bagdeabhishek.github.io/twitterAnalysis) post.