Instructions to use OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B")
model = AutoModelWithLMHead.from_pretrained("OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B

SGLang

How to use OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B 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 "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B" \
    --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": "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B",
		"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 "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B" \
        --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": "OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B with Docker Model Runner:
```
docker model run hf.co/OsamaMo/Arabic_Text-To-SQL_using_Qwen2.5-1.5B
```

OsamaMo commited on Mar 6, 2025

Commit

9864f98

verified ·

1 Parent(s): f3f5e56

Training in progress, step 500

Browse files

This view is limited to 50 files because it contains too many changes. See raw diff

Files changed (50) hide show

.gitattributes +1 -0
LLaMA-Factory/src/llamafactory/__pycache__/__init__.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/__pycache__/cli.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/__pycache__/launcher.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/api/__pycache__/__init__.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/api/__pycache__/app.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/api/__pycache__/chat.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/api/__pycache__/common.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/api/__pycache__/protocol.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/chat/__pycache__/__init__.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/chat/__pycache__/base_engine.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/chat/__pycache__/chat_model.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/chat/__pycache__/hf_engine.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/chat/__pycache__/vllm_engine.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/__pycache__/__init__.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/__pycache__/collator.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/__pycache__/converter.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/__pycache__/data_utils.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/__pycache__/formatter.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/__pycache__/loader.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/__pycache__/mm_plugin.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/__pycache__/parser.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/__pycache__/template.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/__pycache__/tool_utils.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/__init__.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/feedback.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/pairwise.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/pretrain.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/processor_utils.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/supervised.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/data/processor/__pycache__/unsupervised.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/eval/__pycache__/__init__.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/eval/__pycache__/evaluator.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/eval/__pycache__/template.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/extras/__pycache__/__init__.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/extras/__pycache__/constants.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/extras/__pycache__/env.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/extras/__pycache__/logging.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/extras/__pycache__/misc.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/extras/__pycache__/packages.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/extras/__pycache__/ploting.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/hparams/__pycache__/__init__.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/hparams/__pycache__/data_args.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/hparams/__pycache__/evaluation_args.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/hparams/__pycache__/finetuning_args.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/hparams/__pycache__/generating_args.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/hparams/__pycache__/model_args.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/hparams/__pycache__/parser.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/hparams/__pycache__/training_args.cpython-310.pyc +0 -0
LLaMA-Factory/src/llamafactory/model/__pycache__/__init__.cpython-310.pyc +0 -0

@@ -44,3 +44,4 @@ LLaMA-Factory/wandb/run-20250305_224606-f4sva5ub/run-f4sva5ub.wandb filter=lfs d
 LLaMA-Factory/wandb/run-20250305_225658-acin29x5/run-acin29x5.wandb filter=lfs diff=lfs merge=lfs -text
 datasets/llamafactory-finetune-data/train.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text