|
|
--- |
|
|
license: afl-3.0 |
|
|
datasets: |
|
|
- 0xZee/dataset-CoT-Advanced-Calculus-268 |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- Qwen/Qwen3-0.6B |
|
|
pipeline_tag: text-generation |
|
|
library_name: transformers |
|
|
tags: |
|
|
- qwen3 |
|
|
- symbioticai |
|
|
- symbioticllm |
|
|
- discrepancy_calculus |
|
|
- ai |
|
|
- llm |
|
|
- text |
|
|
--- |
|
|
# SymbioticLM-1B |
|
|
|
|
|
**Model Type**: Hybrid Symbolic–Transformer |
|
|
**Base Model**: Qwen-1B |
|
|
**Framework**: PyTorch + HuggingFace Transformers |
|
|
**Purpose**: Lightweight, memory-augmented reasoning model for CPU and embedded inference |
|
|
|
|
|
--- |
|
|
|
|
|
## Overview |
|
|
|
|
|
SymbioticLM-1B is the compact version of the SymbioticAI architecture. It fuses Qwen’s rotary transformer design with a symbolic processing pipeline and a persistent episodic memory. Though smaller in parameter count, it retains the full cognitive engine: symbolic memory, dynamic thought evolution, and entropy-gated control. |
|
|
|
|
|
This model is ideal for symbolic reasoning in constrained environments — like research agents, lightweight assistants, and memory-efficient logical processing. |
|
|
|
|
|
--- |
|
|
|
|
|
## Architecture Highlights |
|
|
|
|
|
- **Backbone**: Qwen-1B rotary transformer |
|
|
- **Symbolic Dim**: 1024 |
|
|
- **Symbolic Modules**: |
|
|
- ThoughtDynamicsLNN |
|
|
- CrystallineProcessor (DNAConv GNN) |
|
|
- LiquidThoughtProcessor |
|
|
- HelicalDNAProcessor |
|
|
- **Memory**: 2048 symbolic vectors with entropic and contextual retrieval |
|
|
- **Dream Mode**: Symbolic simulation with ThoughtGenerator |
|
|
|
|
|
--- |
|
|
|
|
|
## Files Included |
|
|
|
|
|
| File | Description | |
|
|
|--------------------------|-------------------------------------------------------| |
|
|
| `model.bin` | PyTorch model weights | |
|
|
| `model.safetensors` | SafeTensor weights | |
|
|
| `memory.pt` | Serialized symbolic memory vectors | |
|
|
| `config.json` | Model architecture config | |
|
|
| `generation_config.json` | Generation strategy configuration | |
|
|
| `tokenizer.json` | Tokenizer including custom symbolic tags | |
|
|
| `added_tokens.json` | Special tokens such as `<THM>`, `<LEM>`, `<D_IF>` | |
|
|
| `special_tokens_map.json`| Tokenizer-to-logic mappings | |
|
|
|
|
|
--- |
|
|
|
|
|
## Intended Uses |
|
|
|
|
|
- CPU-optimized symbolic inference |
|
|
- Educational agents with memory |
|
|
- Graph-based explanation generation |
|
|
- Procedural planning, math modeling, small-code generation |
|
|
|
|
|
--- |
|
|
|
|
|
## Limitations |
|
|
|
|
|
- Less fluent in free-form language than larger variants |
|
|
- Symbolic accuracy increases with memory curation |
|
|
- Dreaming requires warm-up or symbolic seeding for complex queries |
|
|
|
|
|
--- |
|
|
|
|
|
## Citations |
|
|
|
|
|
|
|
|
Symbolic components are rooted in cognitive modeling and discrepancy calculus research. |
|
|
|
