Instructions to use deviprasadt/zentis-auditos-7b-v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deviprasadt/zentis-auditos-7b-v4 with Transformers:

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

pipe = pipeline("text-generation", model="deviprasadt/zentis-auditos-7b-v4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deviprasadt/zentis-auditos-7b-v4")
model = AutoModelForCausalLM.from_pretrained("deviprasadt/zentis-auditos-7b-v4")
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 deviprasadt/zentis-auditos-7b-v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deviprasadt/zentis-auditos-7b-v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deviprasadt/zentis-auditos-7b-v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deviprasadt/zentis-auditos-7b-v4

SGLang

How to use deviprasadt/zentis-auditos-7b-v4 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 "deviprasadt/zentis-auditos-7b-v4" \
    --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": "deviprasadt/zentis-auditos-7b-v4",
		"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 "deviprasadt/zentis-auditos-7b-v4" \
        --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": "deviprasadt/zentis-auditos-7b-v4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deviprasadt/zentis-auditos-7b-v4 with Docker Model Runner:
```
docker model run hf.co/deviprasadt/zentis-auditos-7b-v4
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Zentis AuditOS-7B

Proprietary model — Zentis AI / Techvantage.ai

A domain-adapted version of Qwen2.5-7B-Instruct fine-tuned for internal audit tasks in BFSI and platform/e-commerce contexts.

Capabilities

Audit finding generation with structured JSON output
Regulatory clause mapping (FSSAI, CGST, DPDP Act, Consumer Protection Act)
Anomaly classification from tabular audit data
Multi-agent audit persona simulation (Lead Auditor, Skeptical Watchdog, Detail Perfectionist, Compliance Guardian)
Control extraction from regulatory documents

Output Schema

All findings are returned as JSON arrays conforming to the AuditOS 2.0 finding schema:

control_id, control_description
evidence_summary
regulator_clause_reference, policy_clause_reference
finding_description
evidence_sufficiency_score (0–1)
regulatory_exposure_score (0–1)
suggested_severity (High/Medium/Low/Observation)
confidence_score (0–1)
anomalous_items (list of specific data-grounded items)

Intended Use

Internal use within the Zentis AuditOS platform. Not for external distribution.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for deviprasadt/zentis-auditos-7b-v4

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Adapter

(2107)

this model