Symbiotic-1B/README.md

license, datasets, language, base_model, pipeline_tag, library_name, tags

license	datasets	language	base_model	pipeline_tag	library_name	tags
afl-3.0	0xZee/dataset-CoT-Advanced-Calculus-268	en	Qwen/Qwen3-0.6B	text-generation	transformers	qwen3 symbioticai symbioticllm discrepancy_calculus ai llm text convergentintel

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

---

Discrepancy Calculus Foundation

This model is part of the Convergent Intelligence LLC: Research Division portfolio. All models in this portfolio are developed under the Discrepancy Calculus (DISC) framework — a measure-theoretic approach to understanding and controlling the gap between what a model should produce and what it actually produces.

DISC treats training singularities (loss plateaus, mode collapse, catastrophic forgetting) not as failures to be smoothed over, but as structural signals that reveal the geometry of the learning problem. Key concepts:

• Discrepancy Operator (D): Measures the gap between expected and observed behavior at each training step
• Jump Sets: Boundaries where model behavior changes discontinuously — these are features, not bugs
• Ghost Imprinting: Teacher knowledge that transfers to student models through weight-space topology rather than explicit distillation signal

For the full mathematical treatment, see Discrepancy Calculus: Foundations and Core Theory (DOI: 10.57967/hf/8194).

Citation chain: Structure Over Scale (DOI: 10.57967/hf/8165) → Three Teachers to Dual Cognition (DOI: 10.57967/hf/8184) → Discrepancy Calculus (DOI: 10.57967/hf/8194)

Citations

Symbolic components are rooted in cognitive modeling and discrepancy calculus research.

---

Convergent Intelligence Portfolio

Part of the Symbiotic AI Series by Convergent Intelligence LLC: Research Division

Related Models

Model	Downloads	Format
Symbiotic-8B	4	HF
Symiotic-14B	3	HF
Symbiotic-Beta	3	HF

Top Models from Our Lab

Model	Downloads
Qwen3-1.7B-Thinking-Distil	501
LFM2.5-1.2B-Distilled-SFT	342
Qwen3-1.7B-Coder-Distilled-SFT	302
Qwen3-0.6B-Distilled-30B-A3B-Thinking-SFT-GGUF	203
Qwen3-1.7B-Coder-Distilled-SFT-GGUF	194

Total Portfolio: 41 models | 2,781 total downloads

Last updated: 2026-03-28 12:57 UTC

---

From the Convergent Intelligence Portfolio

DistilQwen Collection — Our only BF16 series. Proof-weighted distillation from Qwen3-30B-A3B → 1.7B and 0.6B on H100. Three teacher variants (Instruct, Thinking, Coder), nine models, 2,788 combined downloads. The rest of the portfolio proves structure beats scale on CPU. This collection shows what happens when you give the methodology real hardware.

Top model: Qwen3-1.7B-Coder-Distilled-SFT — 508 downloads

Full methodology: Structure Over Scale (DOI: 10.57967/hf/8165)

Convergent Intelligence LLC: Research Division