Instructions to use ReySajju742/Shaista-pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ReySajju742/Shaista-pro with Transformers:

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

pipe = pipeline("text-generation", model="ReySajju742/Shaista-pro")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ReySajju742/Shaista-pro")
model = AutoModelForCausalLM.from_pretrained("ReySajju742/Shaista-pro")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ReySajju742/Shaista-pro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ReySajju742/Shaista-pro"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ReySajju742/Shaista-pro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ReySajju742/Shaista-pro

SGLang

How to use ReySajju742/Shaista-pro 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 "ReySajju742/Shaista-pro" \
    --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": "ReySajju742/Shaista-pro",
		"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 "ReySajju742/Shaista-pro" \
        --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": "ReySajju742/Shaista-pro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ReySajju742/Shaista-pro with Docker Model Runner:
```
docker model run hf.co/ReySajju742/Shaista-pro
```

🌸 Shaista-pro (Full Weights)

Shaista-pro ایک اعلیٰ معیار کا اردو زبان کا ماڈل ہے جسے Qalb-1.0-8B-Instruct سے فائن ٹیون کیا گیا ہے۔ اس ریپوزٹری میں مکمل ماڈل ویٹس (16.1 GB) شامل ہیں، جو اردو متن کی تخلیق، منطقی استدلال، شاعری اور ہدایات پر عمل درآمد میں بہترین کارکردگی کو یقینی بناتے ہیں۔

📋 Model Details

Attribute	Details
Developer	ReySajju742
Model Type	Causal Language Model (Full Weights)
Base Model	Llama-3 8B (Qalb-1.0-8B-Instruct)
Language(s)	Urdu (Primary), English (Secondary)
License	Apache 2.0
Context Length	8,192 tokens
Precision	BF16
Parameters	8 Billion

🚀 Quick Start

Prerequisites

پہلے ضروری لائبریریز انسٹال کریں:

pip install transformers torch accelerate

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for ReySajju742/Shaista-pro

Base model

unsloth/Meta-Llama-3.1-8B

Finetuned

enstazao/Qalb-1.0-8B-Instruct

Finetuned

(2)

this model