Text Generation
Transformers
Safetensors
granite
cybersecurity
defensive-security
infrastructure-as-code
dora
rslora
canadian-ai
simpledirect
vinci
conversational
Instructions to use simpledirect/Vinci-Cyber-30B-1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use simpledirect/Vinci-Cyber-30B-1.0 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="simpledirect/Vinci-Cyber-30B-1.0") 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("simpledirect/Vinci-Cyber-30B-1.0") model = AutoModelForCausalLM.from_pretrained("simpledirect/Vinci-Cyber-30B-1.0", 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 simpledirect/Vinci-Cyber-30B-1.0 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "simpledirect/Vinci-Cyber-30B-1.0" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "simpledirect/Vinci-Cyber-30B-1.0", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/simpledirect/Vinci-Cyber-30B-1.0
- SGLang
How to use simpledirect/Vinci-Cyber-30B-1.0 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 "simpledirect/Vinci-Cyber-30B-1.0" \ --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": "simpledirect/Vinci-Cyber-30B-1.0", "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 "simpledirect/Vinci-Cyber-30B-1.0" \ --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": "simpledirect/Vinci-Cyber-30B-1.0", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use simpledirect/Vinci-Cyber-30B-1.0 with Docker Model Runner:
docker model run hf.co/simpledirect/Vinci-Cyber-30B-1.0
Add 8B/30B family comparison and which-model-to-use guidance; state plainly that the head-to-head capability comparison is not yet drawable
Browse files
README.md
CHANGED
|
@@ -117,6 +117,43 @@ an edit that resolves the finding *and* leaves the file valid — which is why t
|
|
| 117 |
model gets each one right is exactly what the evaluations listed below will establish, and those
|
| 118 |
numbers are not published here yet.
|
| 119 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
## At a glance
|
| 121 |
|
| 122 |
| Property | Value |
|
|
|
|
| 117 |
model gets each one right is exactly what the evaluations listed below will establish, and those
|
| 118 |
numbers are not published here yet.
|
| 119 |
|
| 120 |
+
## Which model should you use
|
| 121 |
+
|
| 122 |
+
There are two models in this family. They were trained on **the same 96-row corpus with the same
|
| 123 |
+
recipe** — same rank, same scaling, same loss, same three behaviours. The only deliberate difference
|
| 124 |
+
is the size of the parent they were applied to.
|
| 125 |
+
|
| 126 |
+
| | [Vinci Cyber 8B 1.0](https://huggingface.co/simpledirect/Vinci-Cyber-8B-1.0) | **Vinci Cyber 30B 1.0** (this model) |
|
| 127 |
+
|---|---|---|
|
| 128 |
+
| Parameters | ~8B | ~28.87B |
|
| 129 |
+
| Parent | Granite 4.1 8B | Granite 4.1 30B |
|
| 130 |
+
| Layers | 40 | 64 |
|
| 131 |
+
| Weights on disk | ~16.8 GB, one file | ~57.7 GB, two shards |
|
| 132 |
+
| Memory in bf16 | roughly 17 GB | roughly 58 GB before runtime overhead |
|
| 133 |
+
| Runs on | a single 24 GB card | a single 80 GB card, or two smaller ones |
|
| 134 |
+
| Training corpus | identical — 96 rows, same digest | identical — 96 rows, same digest |
|
| 135 |
+
| Training recipe | identical — DoRA + rsLoRA, r=32, α=64 | identical — DoRA + rsLoRA, r=32, α=64 |
|
| 136 |
+
| IaC repair result | published: parent 0/8 → **4/8**, restraint 22/22 | **measured, publication held** pending scorer qualification |
|
| 137 |
+
| Licence | Apache-2.0 | Apache-2.0 |
|
| 138 |
+
|
| 139 |
+
**Use the 8B if** you want the published, reviewed result today; you are running on one consumer or
|
| 140 |
+
mid-range card; you are putting the model in a loop where latency matters; or you are evaluating
|
| 141 |
+
whether this approach fits your workflow at all. It is the model with numbers you can check right now.
|
| 142 |
+
|
| 143 |
+
**Use the 30B if** you have the memory budget and want the larger parent's headroom — more general
|
| 144 |
+
knowledge behind the same specialization, and more capacity for longer files and more context around
|
| 145 |
+
a finding.
|
| 146 |
+
|
| 147 |
+
🔴 **What we will not tell you yet: which one repairs more findings.** The 30B's in-domain result is
|
| 148 |
+
measured and held back pending independent qualification of the scoring instrument, so a head-to-head
|
| 149 |
+
capability comparison cannot honestly be drawn here. Bigger parent is a reason to *expect* more; it
|
| 150 |
+
is not evidence of it, and we are not going to dress expectation up as a result. When the instrument
|
| 151 |
+
is qualified, this section gets the comparison — or it gets the news that scale did not help.
|
| 152 |
+
|
| 153 |
+
If you need broad CVE repair across languages rather than IaC security findings, **use something
|
| 154 |
+
else.** The 8B's out-of-domain benchmark showed no measurable improvement over its parent, and
|
| 155 |
+
nothing suggests the 30B changes that. This family is narrow on purpose.
|
| 156 |
+
|
| 157 |
## At a glance
|
| 158 |
|
| 159 |
| Property | Value |
|