Vinci Cyber 123B 1.0 is an open-weight model for defensive infrastructure review and targeted remediation, fine-tuned in Canada from Mistral AI's Devstral 2 123B. The released merged weights have now been tested directly, alongside their parent and the available GGUF formats. Focused repairs. Restraint on correct configuration. Weights you can run yourself. On the V2-B neutral-review test, the released BF16 model preserved 24/24 correct configurations and produced 18/24 scanner-credited repairs, all 18 passing offline provider-schema validation. Its parent repaired 17/24 and preserved 0/24. On the second set, V2-A, Cyber again preserved 24/24, but repaired 9/24 versus the parent's 15/24.…
Open weights
other
125B parameters
262,144 tokens
transformers
An experimental post-training transfer study. We applied the Vinci SFT + DPO character recipe to mistralai/Mistral-7B-Instruct-v0.3 to answer one question: does character training developed on a different model lineage transfer to this one? Apache-2.0, 7.25B, drop-in with transformers. This uses a retired base, and we are saying so first. Mistral lists Mistral 7B Instruct v0.3 as retired as of 30 March 2025 (deprecated 30 November 2024), with Ministral 3 8B as the recommended replacement. "Retired" is Mistral's own lifecycle term. The open weights remain downloadable on Hugging Face under Apache-2.0. We selected this base for continuity with our earlier experiments, not because it is…
Open weights
apache-2.0
7.2B parameters
32,768 tokens
transformers
Canadian-developed. Open weights. Focused on defensive infrastructure. Vinci-Cyber-30B-1.0 is a narrow, verifier-grounded Infrastructure-as-Code security specialist of approximately 28.87B parameters, developed by SimpleDirect, a Canadian AI Lab, from IBM Granite 4.1 30B using a small verifier-grounded cybersecurity training corpus. That scope is the claim, and it is deliberately narrow. It reads a Terraform or OpenTofu file and a finding against it, and answers with an edit that applies — or with NOEDIT when the file is already correct. Thirteen Terraform/OpenTofu files, each carrying one real security misconfiguration, none of them in the training corpus. Plus 22 files that are already…
Open weights
apache-2.0
28.9B parameters
131,072 tokens
transformers
Canadian-developed. Open weights. Focused on defensive infrastructure. Vinci-Cyber-8B-1.0 is an 8B-class security-focused adaptation of IBM Granite 4.1 8B, developed by SimpleDirect, a Canadian AI lab. Its training centres on three infrastructure-as-code behaviours: proposing repairs, leaving clean configurations unchanged, and recovering from unsuccessful attempts. The release gives security engineers, infrastructure teams, and researchers full model weights to evaluate, self-host, and adapt under Apache-2.0. It is intended for human-reviewed defensive workflows—not unattended changes to production infrastructure. Your infrastructure. Your review process. Open weights to build on. The…
Open weights
apache-2.0
8.4B parameters
131,072 tokens
transformers
GGUF distributions of SimpleDirect’s Canadian-developed, open-weight infrastructure-security model. This repository provides GGUF conversions of Vinci-Cyber-8B-1.0, the defensive infrastructure-as-code adaptation developed by SimpleDirect, a Canadian AI lab, from IBM Granite 4.1 8B. The intended application is human-reviewed security work on infrastructure you own or are authorized to assess. The full-weight model’s training centres on repair, no-change, and recovery examples. These are intended behaviours, not guarantees of correct or safe operation. The immediate source is Vinci-Cyber-8B-1.0. Its underlying parent is IBM Granite 4.1 8B, pinned to revision…
Open weights
apache-2.0
GGUF (quantized) builds of Vinci Piccolo, for local inference with Ollama, LM Studio, and llama.cpp. For the full-precision weights, evals, and details, see simpledirect/Vinci-Piccolo-1.0. No GGUF file in this repository has been evaluated. The benchmark figures on the full-precision card were measured on the unquantized bf16 weights, not on any file here. Quantization shifts scores, and with no per-tier measurement this card cannot say in which direction or by how much for any tier. This card therefore publishes no per-tier score, no quality ranking between the tiers, and no recommended tier. The file sizes and memory figures below are measured, and describe storage and memory cost only. A…
Open weights
apache-2.0
gguf
Quantised GGUF builds of Verify what you downloaded against these hashes. Equal file size is not identity. No GGUF file in this repository has been evaluated. Every published measurement was taken on the unquantised weights in the main repo, not on any file here. Quantisation changes model behaviour, and with no per-tier measurement this card cannot say in which direction or by how much for any tier. This card therefore publishes no per-tier score, no quality ranking between the tiers, and no recommended tier. A file's presence in this repository is not a performance claim about that tier, and not a claim of parity with the unquantised weights. All evaluation results, limitations, intended…
Open weights
apache-2.0
GGUF quantizations of simpledirect/Vinci-Bozza-1.0 for local inference with Ollama, LM Studio, and llama.cpp. Text-only. The source model is multimodal (image-text-to-text); these GGUF conversions include the language model only — no mmproj / vision projector. For image input, use the safetensors build: simpledirect/Vinci-Bozza-1.0. No GGUF file in this repository has been evaluated. The benchmark figures on the full-precision card were measured on the unquantized bf16 weights, not on any file here. Quantization shifts scores, and with no per-tier measurement this card cannot say in which direction or by how much for any tier. This card therefore publishes no per-tier score, no quality…
Open weights
apache-2.0
GGUF quantizations of simpledirect/Vinci-Cyber-123B-1.0, for llama.cpp and compatible runtimes. Vinci Cyber 123B is designed for defensive infrastructure review and targeted remediation: propose a focused repair when needed, and leave correct configuration alone. Three formats. Direct task measurements. A clearer deployment choice. All three tiers have now been evaluated on the V2-B neutral-review infrastructure test. Q80 matched the released BF16 model's task outcomes: 18/24 repairs and 24/24 correct configurations unchanged. Q5KM repaired 12/24 and Q4KM 11/24; both preserved 24/24 correct inputs. Every credited repair passed the reported offline provider-schema check. Choose from Q80…
Open weights
other
Quantized GGUF conversions of simpledirect/Vinci-Cyber-30B-1.0, a narrow, verifier-grounded Infrastructure-as-Code security specialist developed by SimpleDirect, a Canadian AI Lab, from IBM Granite 4.1 30B. See the main repository for what the model does, how it was trained, and its evaluation status. What this repository establishes, in one paragraph. All four tiers convert completely (578/578 tensors), carry faithful architecture metadata (14/14 fields), load and generate on CUDA with zero NaN and zero errors, and have had their distributional distortion against the BF16 quant master measured per token and reported below. What it does not establish is capability: no tier was benchmarked…
Open weights
apache-2.0
Vinci Piccolo is a small, open-weight chat model fine-tuned for character and honesty — the first model in the Vinci family from SimpleDirect. The character you'd want in an AI, open and small enough to run yourself. Try it: chat app — free · ollama run hf.co/simpledirect/Vinci-Piccolo-1.0-GGUF Weight-file size is not a runtime-memory requirement — model loading, KV cache, context length and batching all need memory beyond the weights. See Hardware requirements below for the figures we do give. Most fine-tuning optimizes for capability. Vinci Piccolo is fine-tuned for something else: a consistent character and an honest disposition. It is trained against a written, public Constitution that…
Open weights
apache-2.0
4.5B parameters
262,144 tokens
transformers
Vinci Bozza is a 9-billion-parameter open-weight model, fine-tuned from Qwen 3.5-9B with SimpleDirect's Constitution and character training. It is a disposition tune, not a capability retrain. We did not try to make the base model smarter. We tried to make it more honest — and then we measured what that cost. Safer and more honest on the measures below, with general knowledge holding. Strict instruction-following, tool abstention and multi-turn task-holding paid for it. All of it is below, at the same prominence as the gains. The rows above are configuration and artifact values read out of this repository, not validated results. A context length in a config file is a limit the model will…
Open weights
apache-2.0
9.4B parameters
262,144 tokens
transformers
