Instructions to use Vicen-te/qwen3.5-2b-sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vicen-te/qwen3.5-2b-sql with Transformers:

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

pipe = pipeline("text-generation", model="Vicen-te/qwen3.5-2b-sql")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vicen-te/qwen3.5-2b-sql")
model = AutoModelForCausalLM.from_pretrained("Vicen-te/qwen3.5-2b-sql")
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 Settings

vLLM

How to use Vicen-te/qwen3.5-2b-sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vicen-te/qwen3.5-2b-sql"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vicen-te/qwen3.5-2b-sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Vicen-te/qwen3.5-2b-sql

SGLang

How to use Vicen-te/qwen3.5-2b-sql 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 "Vicen-te/qwen3.5-2b-sql" \
    --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": "Vicen-te/qwen3.5-2b-sql",
		"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 "Vicen-te/qwen3.5-2b-sql" \
        --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": "Vicen-te/qwen3.5-2b-sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Vicen-te/qwen3.5-2b-sql with Docker Model Runner:
```
docker model run hf.co/Vicen-te/qwen3.5-2b-sql
```

qwen3.5-2b-sql / README.md

Vicen-te

Super-squash branch 'main' using huggingface_hub

8619cb0 28 days ago

preview code

Raw

History Blame Contribute Delete

1.4 kB

metadata

license: apache-2.0
base_model: Qwen/Qwen3.5-2B
library_name: transformers
tags:
  - text2sql
  - sql
  - qwen3.5
  - fine-tuned
language:
  - en
pipeline_tag: text-generation
datasets:
  - Vicen-te/sql-create-context-mini

Qwen3.5-2B · SQL (merged)

Qwen/Qwen3.5-2B with a LoRA SQL adapter merged in. Drop-in replacement for the base — same architecture, same tokenizer, no PEFT runtime dependency.

Usage with transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("Vicen-te/qwen3.5-2b-sql")
model = AutoModelForCausalLM.from_pretrained("Vicen-te/qwen3.5-2b-sql", dtype="auto", device_map="auto")

Usage with vLLM

vllm serve Vicen-te/qwen3.5-2b-sql --max-model-len 4096 --served-model-name sql-ft

Training

Base model: Qwen/Qwen3.5-2B
Method: LoRA (rank=16, α=32) → merged via peft.merge_and_unload()
Dataset: Vicen-te/sql-create-context-mini — 300 train / 200 eval
Recipe: 3 epochs, bf16, effective batch 16, cosine LR 2e-4

Evaluation

Compared against the base model on a held-out 200-example split. See the project repo for the full report (executable accuracy, exact match, BLEU, latency, 4-bit quantization trade-off).

License

Apache 2.0, inherited from the base model.