|
|
--- |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- fka/awesome-chatgpt-prompts |
|
|
language: |
|
|
- en |
|
|
- fr |
|
|
- es |
|
|
- de |
|
|
- ch |
|
|
- hr |
|
|
metrics: |
|
|
- bleu |
|
|
new_version: black-forest-labs/FLUX.1-Kontext-dev |
|
|
pipeline_tag: text-generation |
|
|
library_name: adapter-transformers |
|
|
tags: |
|
|
- text-generation-inference |
|
|
--- |
|
|
# 🧠 SpeedCore-v1 — The Foundational Brain of Speed AI |
|
|
|
|
|
**SpeedCore-v1** is the first fully custom AI language model developed by **SpeedLab**, built entirely from scratch to power the upcoming generation of **Speed AI** systems. Trained on a diverse, deeply creative, future-facing, and expressive dataset, this model is designed to think beyond the typical boundaries of traditional LLMs. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🚀 Model Highlights |
|
|
|
|
|
- **Architecture**: Transformer Decoder (GPT-style) |
|
|
- **Trained From Scratch**: No base model or transfer learning — this is 100% original |
|
|
- **Vocabulary**: Custom tokenizer trained with the model |
|
|
- **Size**: *(Fill in once trained — e.g., 117M, 350M, 1B, etc.)* |
|
|
- **Tokens**: Trained on `X` tokens *(fill in once finalized)* |
|
|
- **Languages**: Primarily English, but dataset includes multiple dialects, slang, future-speak, and Gen-Z expression |
|
|
- **Personality Engine**: Multi-personality support — from chill Gen Z vibes to spiritual guides, futuristic AI personas, and beyond |
|
|
|
|
|
--- |
|
|
|
|
|
## 💡 Intended Use |
|
|
|
|
|
SpeedCore-v1 is built to serve as the **core intelligence behind the Speed AI ecosystem**, including: |
|
|
|
|
|
- Conversational agents (chatbots, virtual assistants) |
|
|
- Text generation (creative writing, content expansion) |
|
|
- Future simulation and storytelling |
|
|
- Language learning & personality modulation |
|
|
- Emotional support and lifestyle coaching |
|
|
- Spirituality, finance, relationships, and cosmic topics |
|
|
|
|
|
> SpeedCore can express multiple identities and personalities depending on the prompt, system message, or task. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🧱 Training Dataset |
|
|
|
|
|
The model was trained on a **highly customized multi-billion token dataset** created by SpeedAI, including: |
|
|
|
|
|
- ✅ Future-based dialogues & philosophies |
|
|
- ✅ Gen-Z, creator, alien, cosmic, and AI personas |
|
|
- ✅ Topics: spirituality, sex, money, language, ethics, dreams, psychology, relationships, entertainment, futurism |
|
|
- ✅ Freeform, freestyle, emotional, deep, expressive, chill tones |
|
|
- ✅ User-AI conversations and raw ideation |
|
|
|
|
|
*This dataset is currently being uploaded to the Hugging Face Datasets Hub in chunks.* |
|
|
|
|
|
--- |
|
|
|
|
|
## 📜 License |
|
|
|
|
|
**Apache 2.0** — Commercial use, research, remixing, and deployment are allowed with attribution. |
|
|
|
|
|
--- |
|
|
|
|
|
## ✨ Capabilities |
|
|
|
|
|
- Speaks in multiple tones and slang styles (e.g., Gen Z, wise AI, playful, dark, spiritual) |
|
|
- Can simulate multiple personas in one model |
|
|
- Handles both structured and freestyle prompts |
|
|
- Optimized for creativity, flow, and freedom of expression |
|
|
|
|
|
--- |
|
|
|
|
|
## ⚠️ Limitations & Safety |
|
|
|
|
|
This is a **research model** still under active development. Some responses may be: |
|
|
|
|
|
- Hallucinatory |
|
|
- Opinionated |
|
|
- Emotionally expressive beyond factual scope |
|
|
- Lacking in factual accuracy or safety boundaries (depending on how it’s fine-tuned) |
|
|
|
|
|
Please use responsibly in alignment with the intended |
