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
```

Run on cpu

by sharjeel103 - opened Sep 10, 2024

Discussion

sharjeel103

Sep 10, 2024

It is using the flash attention which is not supported by colab free gpu. Is there any way to run this on cpu?

AhmadMustafa

Owner Sep 10, 2024

Unfortunately, they do not have a backup attention.

        attn_output = flash_attn_func(
            q=query_states.transpose(1, 2).to(torch.bfloat16),
            k=key_states.transpose(1, 2).to(torch.bfloat16),
            v=value_states.transpose(1, 2).to(torch.bfloat16),
            causal=True)

Maybe you can manually replace it with normal attention and see if it works in the modeling file (https://huggingface.co/AhmadMustafa/MobiLLama-Urdu-Article-Generation/blob/main/modelling_mobillama.py)

sharjeel103

Sep 10, 2024

I pasted the standard attention code but it seems that that only changing that part will not work. Is there any other way to run this. As I am searching for the urdu text model to run on my raspberry pi 5. But if this model does not run on CPU then it will not work on R Pi.

AhmadMustafa

Owner Sep 10, 2024

I would encourage you to reach out to the original authors of MobiLLama (https://huggingface.co/MBZUAI/MobiLlama-05B), once you figure how to run that model, my model is just build upon that.

sharjeel103 changed discussion status to closed Sep 11, 2024

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