|
Download README.md from FelipeWarOFC/WAR: direct link, hf CLI and curl.
- Browser
- Download file 5.13 kB
-
https://huggingface.co/FelipeWarOFC/WAR/resolve/main/README.md
- Command line
-
hf download hf://FelipeWarOFC/WAR/README.md
-
curl -L -o README.md https://huggingface.co/FelipeWarOFC/WAR/resolve/main/README.md
5.13 kB
| language: | |
| - en | |
| - pt | |
| license: mit | |
| library_name: pytorch | |
| tags: | |
| - pytorch | |
| - llm | |
| - transformer | |
| - from-scratch | |
| - modular-ai | |
| - safety | |
| - hallucination-detection | |
| - prompt-injection | |
| - swiglu | |
| - rmsnorm | |
| - tpu | |
| datasets: | |
| - HuggingFaceFW/fineweb | |
| - deepset/prompt-injections | |
| - pminervini/HaluEval | |
| base_model_relation: finetune | |
| pipeline_tag: text-generation | |
| # β‘ W.A.R. β Modular Multi-Receptor LLM & Safety Architecture | |
| [](https://opensource.org/licenses/MIT) | |
| [](https://pytorch.org/) | |
| []() | |
| [](https://huggingface.co/datasets/HuggingFaceFW/fineweb) | |
| []() | |
| > π **Read this documentation in:** [English](#-english-documentation) | [PortuguΓͺs](#-documentaΓ§Γ£o-em-portuguΓͺs) | |
| --- | |
| ## π English Documentation | |
| ### Overview | |
| **W.A.R.** is an open-source Large Language Model (LLM) and modular verification ecosystem built **entirely from scratch in pure PyTorch**. Designed and implemented by a 14-year-old independent student researcher from Brazil, the project addresses two of the most critical challenges in modern foundation models β **adversarial prompt injections** and **factual hallucinations** β directly at the architectural level rather than relying on external API wrappers. | |
| The baseline tri-modular pipeline comprises **~1.09B parameters** (1 Promoter + 1 Receptor + 1 Judge) and scales up to **~2.92B parameters** when instantiated with **5 domain-specialized Receptors** via CPU-to-Device dynamic memory swapping. | |
| --- | |
| ### ποΈ Architectural Pipeline (Promoter $\rightarrow$ 5x Receptors $\rightarrow$ Judge) | |
| ```text | |
| [ User Input Prompt ] | |
| β | |
| βΌ | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| β 1. PROMOTER (~229M Params | Bidirectional Transformer Encoder) β | |
| β β’ Inspects full prompt context (is_causal=False) + Masked Mean Pooling β | |
| β β’ Trained on deepset/prompt-injections (1.0 = Safe, 0.0 = Attack) β | |
| ββββββββββββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββββββββββ | |
| β | |
| If Safe (P >= 0.5) & Routed | |
| β | |
| ββββββββββββββββββββ¬βββββββββββ΄βββββββββ¬βββββββββββββββββββ | |
| βΌ βΌ βΌ βΌ | |
| βββββββββββββββ βββββββββββββββ βββββββββββββββ βββββββββββββββ | |
| β Receptor #0 β β Receptor #1 β ... β Receptor #3 β β Receptor #4 β | |
| β (~457M GPT) β β (~457M GPT) β β (~457M GPT) β β (~457M GPT) β | |
| ββββββββ¬βββββββ ββββββββ¬βββββββ ββββββββ¬βββββββ ββββββββ¬βββββββ | |
| ββββββββββββββββββββ΄βββββββββββ¬βββββββββ΄βββββββββββββββββββ | |
| β | |
| Candidate Response (Dynamic Device Swap) | |
| β | |
| βΌ | |
| βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ | |
| β 3. JUDGE (~407M Params | Bidirectional Hallucination Verifier) β | |
| β β’ Warm-started from pretrained Receptor Embeddings + First 20 Blocks β | |
| β β’ Evaluates (Question + Candidate Answer) on pminervini/HaluEval β | |
| ββββββββββββββββββββββββββββββββββββββββ¬βββββββββββββββββββββββββββββββββββββββ | |
| β | |
| If Factual (P >= 0.5) | |
| βΌ | |
| [ Verified Final Output ] |