Instructions to use DavoudMo/persian-slm-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavoudMo/persian-slm-qa with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B")
model = PeftModel.from_pretrained(base_model, "DavoudMo/persian-slm-qa")

Transformers

How to use DavoudMo/persian-slm-qa with Transformers:

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

pipe = pipeline("text-generation", model="DavoudMo/persian-slm-qa")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("DavoudMo/persian-slm-qa", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DavoudMo/persian-slm-qa with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DavoudMo/persian-slm-qa

SGLang

How to use DavoudMo/persian-slm-qa 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 "DavoudMo/persian-slm-qa" \
    --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": "DavoudMo/persian-slm-qa",
		"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 "DavoudMo/persian-slm-qa" \
        --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": "DavoudMo/persian-slm-qa",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DavoudMo/persian-slm-qa with Docker Model Runner:
```
docker model run hf.co/DavoudMo/persian-slm-qa
```

You need to agree to share your Hugging Face information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Persian SLM QA (LoRA adapter)

Private LoRA adapter for Persian Q&A, fine-tuned on top of Qwen/Qwen3-1.7B.

This repo contains adapter weights only (~25 MB). Recipients must also download the base model from Hugging Face.

Adapter settings

PEFT type: LoRA
r: 16
lora_alpha: 32
lora_dropout: 0.05
Target modules: q_proj, k_proj, v_proj, o_proj

Load

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = "Qwen/Qwen3-1.7B"
adapter = "DavoudMo/persian-slm-qa"  # private: must be logged in / have access

tokenizer = AutoTokenizer.from_pretrained(adapter, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    base, torch_dtype="auto", device_map="auto", trust_remote_code=True
)
model = PeftModel.from_pretrained(model, adapter)

Private access

Repo owner adds the collaborator's Hugging Face username under Settings → Collaborators.
Collaborator runs hf auth login (or sets HF_TOKEN) with a token that can read this repo.
Then from_pretrained(adapter) works as usual.

License

Derived from Qwen/Qwen3-1.7B. Follow Qwen's license terms when redistributing or deploying.

Downloads last month: 10

Model tree for DavoudMo/persian-slm-qa

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Adapter

(860)

this model