Instructions to use MaXoN654/RUSQL-0.8B-Text2SQL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MaXoN654/RUSQL-0.8B-Text2SQL with Transformers:

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

pipe = pipeline("text-generation", model="MaXoN654/RUSQL-0.8B-Text2SQL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaXoN654/RUSQL-0.8B-Text2SQL")
model = AutoModelForCausalLM.from_pretrained("MaXoN654/RUSQL-0.8B-Text2SQL", device_map="auto")
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 MaXoN654/RUSQL-0.8B-Text2SQL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MaXoN654/RUSQL-0.8B-Text2SQL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaXoN654/RUSQL-0.8B-Text2SQL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MaXoN654/RUSQL-0.8B-Text2SQL

SGLang

How to use MaXoN654/RUSQL-0.8B-Text2SQL 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 "MaXoN654/RUSQL-0.8B-Text2SQL" \
    --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": "MaXoN654/RUSQL-0.8B-Text2SQL",
		"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 "MaXoN654/RUSQL-0.8B-Text2SQL" \
        --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": "MaXoN654/RUSQL-0.8B-Text2SQL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MaXoN654/RUSQL-0.8B-Text2SQL with Docker Model Runner:
```
docker model run hf.co/MaXoN654/RUSQL-0.8B-Text2SQL
```

MaXoN654 commited on Jul 17

Commit

6cd4a5f

verified ·

1 Parent(s): f3c61c6

model card: full-split eval (RU 58.4%, n=2729)

Browse files

Files changed (1) hide show

README.md +28 -13

README.md CHANGED Viewed

@@ -30,27 +30,42 @@ questions** over a database schema with step-by-step reasoning that ends in a fi
 ## Performance Evaluation
 Execution accuracy (predicted SQL executed against SQLite, result-set comparison)
-on a 500-example subset of the held-out Russian eval split:
-| Model | Questions | EX accuracy |
-|---|---|---|
-| Base (zero-shot) | EN | 16.0% |
-| Base (zero-shot) | RU | 15.4% |
-| **RUSQL (this model)** | **RU** | **73.2%** |
-Fine-tuning lifts execution accuracy **from 15.4% to 73.2%** — nearly 5× the base
 model, and well above its English-question ceiling (16.0%).
-Breakdown by SQL complexity:
 | Complexity | n | EX accuracy |
 |---|---|---|
-| Simple | 57 | 73.7% |
-| Moderate | 132 | 81.1% |
-| Complex | 214 | 78.5% |
-| Highly Complex | 97 | 50.5% |
-*Preliminary numbers (n=500, greedy decoding); full-split evaluation will follow.*
 ## Dataset Overview

 ## Performance Evaluation
 Execution accuracy (predicted SQL executed against SQLite, result-set comparison)
+on the **full held-out eval split** (greedy decoding):
+| Model | Questions | n | EX accuracy |
+|---|---|---|---|
+| Base (zero-shot) | EN | 3,032 | 16.0% |
+| Base (zero-shot) | RU | 2,729 | 13.9% |
+| **RUSQL (this model)** | **RU** | **2,729** | **58.4%** |
+Fine-tuning lifts execution accuracy **from 13.9% to 58.4%** — about 4.2× the base
 model, and well above its English-question ceiling (16.0%).
+Breakdown by SQL complexity (RUSQL, RU questions):
 | Complexity | n | EX accuracy |
 |---|---|---|
+| Simple | 259 | 75.7% |
+| Moderate | 858 | 70.3% |
+| Complex | 973 | 55.1% |
+| Highly Complex | 639 | 40.5% |
+Breakdown by question style (RUSQL, RU questions):
+| Style | n | EX accuracy |
+|---|---|---|
+| Formal | 310 | 62.9% |
+| Interrogative | 310 | 62.6% |
+| Multi-turn Dialogue | 270 | 59.6% |
+| Colloquial | 336 | 59.5% |
+| Imperative | 324 | 58.6% |
+| Descriptive | 312 | 58.3% |
+| Concise | 273 | 57.1% |
+| Vague | 310 | 55.5% |
+| Metaphorical | 284 | 50.7% |
+*Full-split evaluation (RU n=2,729 / EN n=3,032), greedy decoding, only 13 of 2,729
+RUSQL generations failed to emit a SQL block.*
 ## Dataset Overview