Instructions to use Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet with Transformers:

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

pipe = pipeline("text-generation", model="Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet")
model = AutoModelForMultimodalLM.from_pretrained("Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet

SGLang

How to use Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet 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 "Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet with Docker Model Runner:
```
docker model run hf.co/Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen2.5-3B-Urdu-Ultimate-Poet

Developed by Khurram Pervez (Khurram123), this model is a high-performance, specialized version of the Qwen2.5-3B architecture, fine-tuned specifically for the nuances of the Urdu language.

🌟 Model Highlights

This "Ultimate" version is the result of a multi-stage training process designed to create a versatile Urdu AI. It excels in three distinct areas:

News & Information: Trained on the XL-Sum dataset to provide accurate and concise summaries of complex Urdu news articles.
Instruction & Chat: Integrated with Urdu-Alpaca data to follow user commands, answer questions, and engage in natural conversation.
Classical & Modern Poetry: Deeply fine-tuned on the Urdu-Poetry-Dataset, allowing it to compose ghazals and nazms with an understanding of Urdu poetic rhythm and vocabulary (including styles like Firaq Gorakhpuri).

🚀 How to Use

You can load this model using the transformers library on any GPU-enabled machine.

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    torch_dtype=torch.float16, 
    device_map="auto"
)

# Example Prompt for Poetry
prompt = "<|im_start|>user\nعنوان 'شامِ ہجراں' پر ایک شعر لکھیں۔<|im_end|>\n<|im_start|>assistant\n"

inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=150, do_sample=True, temperature=0.7)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 2

Safetensors

Model size

3B params

Tensor type

F16

Model tree for Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet

Base model

Qwen/Qwen2.5-3B

Finetuned

(417)

this model

Quantizations

1 model

Khurram123
/

Qwen2.5-3B-Urdu-Ultimate-Poet

Qwen2.5-3B-Urdu-Ultimate-Poet

🌟 Model Highlights

🚀 How to Use

Model tree for Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet

Datasets used to train Khurram123/Qwen2.5-3B-Urdu-Ultimate-Poet