Instructions to use Mr-Vicky-01/sql-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mr-Vicky-01/sql-assistant with Transformers:

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

pipe = pipeline("text-generation", model="Mr-Vicky-01/sql-assistant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mr-Vicky-01/sql-assistant")
model = AutoModelForCausalLM.from_pretrained("Mr-Vicky-01/sql-assistant")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Mr-Vicky-01/sql-assistant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mr-Vicky-01/sql-assistant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mr-Vicky-01/sql-assistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mr-Vicky-01/sql-assistant

SGLang

How to use Mr-Vicky-01/sql-assistant 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 "Mr-Vicky-01/sql-assistant" \
    --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": "Mr-Vicky-01/sql-assistant",
		"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 "Mr-Vicky-01/sql-assistant" \
        --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": "Mr-Vicky-01/sql-assistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Mr-Vicky-01/sql-assistant with Docker Model Runner:
```
docker model run hf.co/Mr-Vicky-01/sql-assistant
```

Mr-Vicky-01 commited on Mar 19, 2025

Commit

2d589f8

verified ·

1 Parent(s): 5f0af16

Update README.md

Browse files

Files changed (1) hide show

README.md +63 -9

README.md CHANGED Viewed

@@ -1,10 +1,7 @@
 ---
-base_model: unsloth/qwen2.5-coder-0.5b-instruct-bnb-4bit
 tags:
 - text-generation-inference
 - transformers
-- unsloth
-- qwen2
 - trl
 - sft
 license: apache-2.0
@@ -12,12 +9,69 @@ language:
 - en
 ---
-# Uploaded  model
-- **Developed by:** Mr-Vicky-01
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/qwen2.5-coder-0.5b-instruct-bnb-4bit
-This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 ---
 tags:
 - text-generation-inference
 - transformers
 - trl
 - sft
 license: apache-2.0
 - en
 ---
+# INFERENCE
+```python
+import time
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+finetuned_model = AutoModelForCausalLM.from_pretrained("Mr-Vicky-01/sql-assistant")
+finetuned_model.to(device)
+tokenizer = AutoTokenizer.from_pretrained("Mr-Vicky-01/sql-assistant")
+prompt = """<|im_start|>system
+<|im_start|>system
+You are a helpful SQL assistant named Securitron. Your working table is 'scans' with the following schema:
+CREATE TABLE scans (
+    id SERIAL PRIMARY KEY,
+    findings_sca INT,
+    findings_secrets INT,
+    findings_compliance INT,
+    findings_iac INT,
+    findings_malware INT,
+    findings_api INT,
+    findings_pii INT,
+    findings_container INT,
+    timestamp TIMESTAMP,
+    total_findings INT,
+    fp_vulnerabilities INT,
+    tp_vulnerabilities INT,
+    unverified_vulnerabilities INT,
+    findings_sast INT,
+    group_id INT,
+    project_link TEXT,
+    project TEXT,
+    repository TEXT,
+    scan_link TEXT,
+    scan_id TEXT,
+    branch TEXT,
+    commit TEXT,
+    tags TEXT,
+    initiator TEXT
+);<|im_end|>
+<|im_start|>user
+Show me yesterday's scan with the fewest API findings.<|im_end|>
+<|im_start|>assistant
+"""
+s = time.time()
+encodeds = tokenizer(prompt, return_tensors="pt",truncation=True).input_ids.to(device)
+text_streamer = TextStreamer(tokenizer, skip_prompt = True)
+# Increase max_new_tokens if needed
+response = finetuned_model.generate(
+        input_ids=encodeds,
+        streamer=text_streamer,
+        max_new_tokens=512,
+        use_cache=True,
+        pad_token_id=151645,
+        eos_token_id=151645,
+        num_return_sequences=1
+    )
+e = time.time()
+print(f'time taken:{e-s}')
+```