Instructions to use ekaya-inc/Ekaya-30B-A3B-community with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ekaya-inc/Ekaya-30B-A3B-community with Transformers:

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

pipe = pipeline("text-generation", model="ekaya-inc/Ekaya-30B-A3B-community")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ekaya-inc/Ekaya-30B-A3B-community")
model = AutoModelForCausalLM.from_pretrained("ekaya-inc/Ekaya-30B-A3B-community")
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 ekaya-inc/Ekaya-30B-A3B-community with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ekaya-inc/Ekaya-30B-A3B-community"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ekaya-inc/Ekaya-30B-A3B-community",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ekaya-inc/Ekaya-30B-A3B-community

SGLang

How to use ekaya-inc/Ekaya-30B-A3B-community 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 "ekaya-inc/Ekaya-30B-A3B-community" \
    --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": "ekaya-inc/Ekaya-30B-A3B-community",
		"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 "ekaya-inc/Ekaya-30B-A3B-community" \
        --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": "ekaya-inc/Ekaya-30B-A3B-community",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ekaya-inc/Ekaya-30B-A3B-community with Docker Model Runner:
```
docker model run hf.co/ekaya-inc/Ekaya-30B-A3B-community
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Ekaya-30B-A3B-community

Fine-tuned Qwen3-30B-A3B for structured SQL generation with ClickHouse.

What's Different

This model produces structured JSON output instead of free-form text:

{
  "output": {
    "sql": {
      "query": "SELECT COUNT(*) FROM users",
      "dialect": "clickhouse",
      "tables_used": ["users"],
      "confidence": 0.95,
      "requires_review": false
    }
  }
}

Metric	Base Qwen3-30B-A3B	This Model
Valid JSON	57%	100%
All fields present	0%	100%
Correct types	0%	100%

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "ekaya-inc/Ekaya-30B-A3B-community",
    torch_dtype="auto",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("ekaya-inc/Ekaya-30B-A3B-community")

prompt = """<|im_start|>system
You are an expert SQL assistant for ClickHouse. Output ONLY valid JSON.
<|im_end|>
<|im_start|>user
Schema: CREATE TABLE users (id UInt64, name String, email String)
Question: Count all users
<|im_end|>
<|im_start|>assistant
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Technical Specifications

Parameter	Value
Base model	Qwen3-30B-A3B (30B total, 3B active via MoE)
Fine-tuning method	QLoRA (r=32, alpha=64)
Quantization	4-bit NF4 during training
Training samples	2,907 synthetic text2sql examples
Domains	8 diverse schemas (e-commerce, healthcare, finance, etc.)
Hardware	NVIDIA DGX Spark (Blackwell)
Training time	~9 hours

LoRA Target Modules

Both attention and expert FFN layers:

Attention: q_proj, k_proj, v_proj, o_proj
Expert FFN: gate_proj, up_proj, down_proj (all 128 experts)

Limitations

SQL correctness not validated: Format is correct, but query logic may have errors
No security training: Not trained to detect SQL injection or enforce RLS
Confidence not calibrated: The confidence field is not yet meaningful
ClickHouse only: Trained specifically for ClickHouse dialect

Intended Use

This is a community preview for developers exploring embeddable text2sql models. Production use should wait for:

SQL quality validation
Security awareness training
Confidence calibration

License

Apache 2.0 (same as base model)

Downloads last month: 1

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for ekaya-inc/Ekaya-30B-A3B-community

Base model

Qwen/Qwen3-30B-A3B-Base

Finetuned

Qwen/Qwen3-30B-A3B

Finetuned

(50)

this model

Quantizations

2 models