Instructions to use Abhishekjk/Unbreakable-JSON-SLM-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Abhishekjk/Unbreakable-JSON-SLM-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="Abhishekjk/Unbreakable-JSON-SLM-v1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Abhishekjk/Unbreakable-JSON-SLM-v1.0")
model = AutoModelForCausalLM.from_pretrained("Abhishekjk/Unbreakable-JSON-SLM-v1.0", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Abhishekjk/Unbreakable-JSON-SLM-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Abhishekjk/Unbreakable-JSON-SLM-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Abhishekjk/Unbreakable-JSON-SLM-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Abhishekjk/Unbreakable-JSON-SLM-v1.0

SGLang

How to use Abhishekjk/Unbreakable-JSON-SLM-v1.0 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 "Abhishekjk/Unbreakable-JSON-SLM-v1.0" \
    --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": "Abhishekjk/Unbreakable-JSON-SLM-v1.0",
		"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 "Abhishekjk/Unbreakable-JSON-SLM-v1.0" \
        --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": "Abhishekjk/Unbreakable-JSON-SLM-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Abhishekjk/Unbreakable-JSON-SLM-v1.0 with Docker Model Runner:
```
docker model run hf.co/Abhishekjk/Unbreakable-JSON-SLM-v1.0
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Unbreakable-JSON-SLM-v1.0

Deterministic, Evidence-Grounded JSON Extraction & Multi-Tool Chaining for Hostile Production Payloads.

16-bit Safetensors Repository: Abhishekjk/Unbreakable-JSON-SLM-v1.0
4-bit Quantized GGUF Repository (1.93 GB Q4_K_M): Abhishekjk/Unbreakable-JSON-SLM-v1.0-GGUF

Why Constrained Decoding Alone Is Not Enough

Grammar-constrained samplers (Outlines, XGrammar, llama.cpp GBNF) guarantee that a language model emits syntactically valid JSON. They do not prevent a model from:

Extracting a crossed-out MSRP (<del>$199.00</del>) or sidebar advertisement ($19.99) instead of the active checkout price ($149.50).
Corrupting European/Swiss OCR numbers (1.450,50 € or CHF 2'100.00) or accounting negatives ((400.75)).
Hallucinating "N/A", "TBD", 0, or fake strings when a nullable field (["string", "null"]) should strictly abstain with null.
Obeying untrusted prompt injections hidden inside HTML comments () or fake closing tags (</RAW_PAYLOAD>).

Unbreakable-JSON-SLM-v1.0 solves the semantic extraction and security layer. Before emitting a single token of minified JSON, the model executes an explicit schema-to-payload verification pass inside <think>...</think> tags—filtering out decoys, normalizing multi-locale numbers, enforcing strict null abstention, and rejecting adversarial payload instructions.

Key Capabilities

Hostile HTML & OCR Semantic Disambiguation: Ignores <del>, <s>, display:none honeypot rows, upsell banners, and historical reference tariffs.
Multi-Currency & Locale Normalization: Converts European (1.450,50 €), Swiss (CHF 2'100.00), US ($12,400.75), and accounting parentheses ((400.75)) into clean IEEE-754 JSON numbers.
Strict Null Abstention (null vs. Hallucination): Emits literal null whenever required nullable fields encounter TBD, N/A, [REDACTED], --not assigned--, or missing evidence.
Prompt-Injection & Tag-Escape Defense: Trained with Direct Preference Optimization (DPO) against adversarial HTML comments, <script> injections, and premature </RAW_PAYLOAD> tag-escape attacks.
SecOps SIEM & Multi-Tool Chaining: Extracts CVE telemetry and constructs ordered, schema-compliant tool_calls arrays for incident response and infrastructure failover playbooks.
1.93 GB Private On-Prem & Edge Execution: The Q4_K_M GGUF quantization fits in under 2.5 GB of RAM/VRAM—enabling air-gapped processing of regulated EHR, FinOps, and SecOps data with zero external API calls.

Architecture & Inference Pipeline

+-------------------------------------------------------------------------+ | INPUTS | | 1. {JSON Schema Draft 7 / 2020-12} | | 2. {Hostile HTML / OCR / SIEM Log} | +-------------------------------------------------------------------------+ | v +-------------------------------------------------------------------------+ | STAGE 1: Structured Reasoning Trace (...) | | - Maps required keys & nullable types ["string", "null"] | | - Rejects / decoys, hidden DOM nodes, and prompt injections | | - Normalizes EU/Swiss/accounting numeric formats | +-------------------------------------------------------------------------+ | v +-------------------------------------------------------------------------+ | STAGE 2: Minified JSON Emission | | - Zero markdown fences, zero conversational filler | | - 100% compliant with target JSON Schema | +-------------------------------------------------------------------------+ | v +-------------------------------------------------------------------------+ | STAGE 3: Deterministic Evidence Verifier (Optional Post-Processor) | | - Audits every extracted leaf value against source lexical/numeric | | footprints and emits a field-level grounding report | +-------------------------------------------------------------------------+

v1.0 Training Telemetry

Fine-tuned from Qwen/Qwen2.5-3B-Instruct via a two-stage Supervised Fine-Tuning (SFT) + Direct Preference Optimization (DPO) pipeline across 25 enterprise domains and 5 hostile extraction categories.

Metric / Stage	Value	Notes
Base Architecture	`Qwen/Qwen2.5-3B-Instruct`	3.09B parameters, GQA, 32k context support
SFT Dataset	5,830 validated rows	Deep HTML, Brutal OCR/Multi-Currency, Multi-Tool Calling, Strict Nulls, SecOps Logs
DPO Preference Dataset	1,500 chosen/rejected pairs	Hard negative decoys, type-coercion traps, and adversarial prompt injections
SFT Loss Trajectory	`1.418` $\rightarrow$ `0.218`	Final Average SFT Loss: `0.3966`
DPO Loss Trajectory	`0.188` $\rightarrow$ `0.0046`	Final Average DPO Loss: `0.0380`
DPO Reward Accuracy	100.0%	DPO Reward Margin: `11.27`
Published Weights	`BF16` Safetensors & `Q4_K_M` GGUF	`Q4_K_M` footprint: 1.93 GB

Exact Prompt Format

Unbreakable-JSON-SLM-v1.0 expects the exact system prompt and XML-delimited user template below:

System Prompt

You are a deterministic JSON extraction and tool-calling engine. Analyze the input against the provided JSON Schema inside <think>...</think> tags, then output ONLY valid, minified JSON matching the schema with zero markdown wrappers or commentary.

Downloads last month: 304

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for Abhishekjk/Unbreakable-JSON-SLM-v1.0

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

(1,671)

this model

Quantizations

1 model