Instructions to use AhmadMustafa/MobiLLama-Urdu-Article-Generation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AhmadMustafa/MobiLLama-Urdu-Article-Generation with Transformers:

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

pipe = pipeline("text-generation", model="AhmadMustafa/MobiLLama-Urdu-Article-Generation", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AhmadMustafa/MobiLLama-Urdu-Article-Generation", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("AhmadMustafa/MobiLLama-Urdu-Article-Generation", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AhmadMustafa/MobiLLama-Urdu-Article-Generation with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AhmadMustafa/MobiLLama-Urdu-Article-Generation

SGLang

How to use AhmadMustafa/MobiLLama-Urdu-Article-Generation 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 "AhmadMustafa/MobiLLama-Urdu-Article-Generation" \
    --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": "AhmadMustafa/MobiLLama-Urdu-Article-Generation",
		"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 "AhmadMustafa/MobiLLama-Urdu-Article-Generation" \
        --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": "AhmadMustafa/MobiLLama-Urdu-Article-Generation",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AhmadMustafa/MobiLLama-Urdu-Article-Generation with Docker Model Runner:
```
docker model run hf.co/AhmadMustafa/MobiLLama-Urdu-Article-Generation
```

Urdu (Pakistan) language Model

by AamirFarooq - opened Apr 2, 2024

Discussion

AamirFarooq

Apr 2, 2024

This model is it available form of ios app?

AhmadMustafa

Owner Apr 2, 2024

Not yet. I don't think this model is fully production ready yet.

AamirFarooq

Apr 2, 2024

I’m not Devloper and not programmer, would you guide me how can I use this model into my mobile, Apple own ios app called shortcuts through this app can I use this model?

AhmadMustafa

Owner Apr 5, 2024

can you tell me your use-case? i haven't tested it on mobile so I am not sure if I can help you here. also it is not production ready I think, it needs some more work right now.

AamirFarooq

Apr 5, 2024

Use case I have small YouTube channel, for my videos I’m looking much accurate transcription for Urdu language,

AhmadMustafa

Owner Apr 5, 2024

This model can not do transcription. It only generates Urdu text. (https://apps.apple.com/us/app/whisper-transcribe-dictation/id6450915714, or https://apps.apple.com/us/app/whisper-transcription/id1668083311?mt=12).
Whisper can do Urdu transcription.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment