Instructions to use adamabuhamdan/tinyllama-sql-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adamabuhamdan/tinyllama-sql-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
model = PeftModel.from_pretrained(base_model, "adamabuhamdan/tinyllama-sql-lora")

Transformers

How to use adamabuhamdan/tinyllama-sql-lora with Transformers:

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

pipe = pipeline("text-generation", model="adamabuhamdan/tinyllama-sql-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("adamabuhamdan/tinyllama-sql-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adamabuhamdan/tinyllama-sql-lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/adamabuhamdan/tinyllama-sql-lora

SGLang

How to use adamabuhamdan/tinyllama-sql-lora 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 "adamabuhamdan/tinyllama-sql-lora" \
    --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": "adamabuhamdan/tinyllama-sql-lora",
		"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 "adamabuhamdan/tinyllama-sql-lora" \
        --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": "adamabuhamdan/tinyllama-sql-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adamabuhamdan/tinyllama-sql-lora with Docker Model Runner:
```
docker model run hf.co/adamabuhamdan/tinyllama-sql-lora
```

tinyllama-sql-lora / README.md

adamabuhamdan

Update README.md

ce1c444 verified 5 months ago

preview code

Raw History Blame Contribute Delete

2.34 kB

	---
	base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
	library_name: peft
	pipeline_tag: text-generation
	tags:
	- base_model:adapter:TinyLlama/TinyLlama-1.1B-Chat-v1.0
	- lora
	- sft
	- transformers
	- trl
	- text-to-sql
	datasets:
	- b-mc2/sql-create-context
	---

	# 🤖 TinyLlama Text-to-SQL (LoRA Adapter)

	هذا النموذج عبارة عن LoRA Adapter تم تدريبه لتعديل سلوك نموذج `TinyLlama-1.1B` ليصبح متخصصاً في تحويل الأسئلة باللغة الطبيعية إلى كود SQL دقيق بناءً على هيكل الجدول (Schema) المعطى له، دون أي ثرثرة زائدة.

	- Developed by: Adam Abu Hamdan
	- Model type: PEFT (LoRA)
	- Language: English (Text & SQL)
	- Finetuned from model: TinyLlama/TinyLlama-1.1B-Chat-v1.0

	---

	## 💡 كيف يعمل النموذج (How to Get Started)

	يمكنك تشغيل هذا النموذج ودمج الأدابتر (الـ 20 ميجابايت) مع النموذج الأساسي باستخدام الكود التالي في بايثون:

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer
	from peft import PeftModel

	BASE_MODEL = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
	ADAPTER_MODEL = "adamabuhamdan/tinyllama-sql-lora"

	# 1. تحميل المترجم والنموذج الأساسي
	tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
	base_model = AutoModelForCausalLM.from_pretrained(
	BASE_MODEL,
	torch_dtype=torch.float16,
	device_map="auto",
	)

	# 2. دمج أوزان LoRA التي قمنا بتدريبها
	model = PeftModel.from_pretrained(base_model, ADAPTER_MODEL)
	model.eval()

	# 3. تجربة توليد كود SQL
	schema = "CREATE TABLE employees (id INT, name TEXT, department TEXT, salary INT);"
	question = "List the names of employees in Engineering earning more than 100000."

	prompt = f"<\|system\|>\nYou are a SQL assistant. Given a table schema and a question, reply with ONLY the SQL query, nothing else.</s>\n<\|user\|>\nSchema:\n{schema}\n\nQuestion: {question}</s>\n<\|assistant\|>\n"

	inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
	with torch.no_grad():
	outputs = model.generate(**inputs, max_new_tokens=100, do_sample=False)

	print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True).strip())