reaperdoesntknow/Symbiotic-8B

TEXT GENERATIONPricing:Input $0.468 / Output $1.82Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:32kTool Calling:SupportedPublished:May 6, 2025License:afl-3.0Architecture:Transformer0.0K Featherless Exclusive Cold

SymbioticLM-8B by reaperdoesntknow is an 8 billion parameter hybrid symbolic-transformer model built on Qwen-8B, featuring a 32768 token context length. It integrates modular symbolic processors and a persistent memory buffer for advanced reasoning. This model excels at long-memory symbolic tasks like theorem generation, logical chaining, and structured reasoning, making it suitable for memory-aware tutoring and context-persistent dialogue systems.

Loading preview...

SymbioticLM-8B: Hybrid Symbolic-Transformer with Persistent Memory

SymbioticLM-8B, developed by reaperdoesntknow (Convergent Intelligence LLC: Research Division), is an 8 billion parameter model based on Qwen-8B, designed for advanced symbolic reasoning and high-fidelity language generation. It uniquely combines a transformer backbone with specialized symbolic processors and a persistent memory buffer, allowing it to retain context and perform complex logical operations across turns. The model operates within a 32768 token context window.

Key Capabilities

  • Hybrid Architecture: Integrates a Qwen-8B transformer with modular symbolic processors (e.g., ThoughtDynamicsLNN, CrystallineProcessor, LiquidThoughtProcessor, HelicalDNAProcessor).
  • Persistent Memory: Features a 2048 symbolic vector memory with entropy-aware retrieval for contextual recall, enabling long-term memory in interactions.
  • Symbolic Reasoning: Excels at tasks requiring deep symbolic cognition, such as theorem generation, logical chaining, and structured reasoning.
  • "Dream Mode": Capable of self-generating symbolic cognition offline.
  • Discrepancy Calculus Foundation: Developed under the DISC framework, which treats training singularities as structural signals for understanding learning geometry.

Good For

  • General Symbolic Reasoning: Ideal for applications requiring logical conversation and complex problem-solving.
  • Memory-Aware Tutoring & Research Assistants: Its persistent memory makes it suitable for educational tools and research support systems that need to recall past interactions.
  • Code & Math Proof Modeling: Specialized for tasks involving formal proofs and mathematical reasoning.
  • Context-Persistent Dialogue Systems: Enables more coherent and contextually aware conversations by retaining information across dialogue turns.