Instructions to use NBAmine/mistral-nemo-text-to-sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NBAmine/mistral-nemo-text-to-sql with Transformers:

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

pipe = pipeline("text-generation", model="NBAmine/mistral-nemo-text-to-sql")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NBAmine/mistral-nemo-text-to-sql")
model = AutoModelForCausalLM.from_pretrained("NBAmine/mistral-nemo-text-to-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]:]))

PEFT
How to use NBAmine/mistral-nemo-text-to-sql with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NBAmine/mistral-nemo-text-to-sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NBAmine/mistral-nemo-text-to-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": "NBAmine/mistral-nemo-text-to-sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NBAmine/mistral-nemo-text-to-sql

SGLang

How to use NBAmine/mistral-nemo-text-to-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 "NBAmine/mistral-nemo-text-to-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": "NBAmine/mistral-nemo-text-to-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 "NBAmine/mistral-nemo-text-to-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": "NBAmine/mistral-nemo-text-to-sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NBAmine/mistral-nemo-text-to-sql with Docker Model Runner:
```
docker model run hf.co/NBAmine/mistral-nemo-text-to-sql
```

Mistral-Nemo-12B-Text-to-SQL

Model Overview

This is the full-precision (BF16), merged version of a Mistral-Nemo-12B model Parameter-Efficient Fine-Tuned for high-performance Text-to-SQL generation. This model is the result of merging LoRA adapters—trained via a two-phase curriculum learning strategy—back into the base weights.

It is designed to serve as the "Source of Truth" for further optimizations (like AWQ or GGUF) and represents the peak predictive performance of the training pipeline before any quantization-related drift.

Base Model: mistralai/Mistral-Nemo-Base-2407
Primary Task: Natural Language to SQL generation with DDL context.
Output Format: Standalone SQL queries compatible with standard SQL engines.

Training Methodology

The model was developed using an MLOps pipeline on dual T4 GPUs in Kaggle.

1. Curriculum Learning Strategy

The model underwent a two-stage training process:

Phase 1 (Syntactic Alignment): Focused on SQL syntax, basic keywords, and simple schema mapping.
Phase 2 (Logical Alignment): Introduced complex reasoning tasks including multiple JOIN operations, nested subqueries, and set operations (UNION, INTERSECT).

2. Fine-Tuning Details

Technique: QLoRA (Rank 16, Alpha 32)
Quantization (during training): 4-bit NF4
Optimizer: Paged AdamW 8-bit
Hardware: 2x NVIDIA T4 (Kaggle).

Evaluation Results

Evaluated on the Spider validation set:

Execution Accuracy (EX): 69.5%
Exact Match (EM): 61.2%
Max Context Length: 2048 tokens

Architecture Specs

The merged weights utilize the standard Mistral-Nemo 12B architecture:

Parameters: 12.2B
Layers: 40
Attention: Grouped Query Attention (GQA) with 8 KV heads.
Vocabulary Size: 128k (Tekken Tokenizer)
VRAM Requirements: ~24GB for inference in BF16/FP16.

Template used during training

prompt = "Context: {DDL}
Question: {NL_QUERY}
Answer:"

Downloads last month: 9

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for NBAmine/mistral-nemo-text-to-sql

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

mistralai/Mistral-Nemo-Instruct-2407