Powerful Vibe coding LLM
AI & ML interests
EpisteLabs, founded in 2024. It is a research and development artificial super intelligence company. We create AI that is aligned and safe that provides best response to humanity. We fine tune LLM using Unsloth. https://github.com/tomtyiu/EpistemeAI-series-Cookbook-SDK
Recent Activity
Hercules Gemma 3N collection
These LLM are aligned and safe AI assistant
-
EpistemeAI/ReasoningCore-Llama-3B-R1-aligned
Text Generation • Updated • 2 • 1 -
EpistemeAI/SAI-DeepCoder-14B-Preview-v1.0
Text Generation • 15B • Updated • 6 -
EpistemeAI/SADeepCoder-1.5B-Preview-v1
Text Generation • 2B • Updated • 2 -
EpistemeAI/SAI-DeepMathCoder-14B-Preview-v1.0
Text Generation • 15B • Updated • 5 • 1
Why limit AGI to one “super brain” when you can have multiple minds in one?
Psyche of Logic, Psyche of Emotion, Psyche of Improv .
-
EpistemeAI/Polypsyche-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto-divergent
Text Generation • 8B • Updated -
EpistemeAI/Polypsyche-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto-Logic
Text Generation • 8B • Updated • 1 -
EpistemeAI/Polypsyche-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto-Empathy
Text Generation • 8B • Updated -
EpistemeAI/Polypsyche-Llama-3.1-8B-Instruct-Agent-0.0031-128K-code-ds-auto-Logic
Text Generation • Updated • 1
Open fine-tuned Gemma, codegemma-2-9b
Fine-tuned Llama 3.1 with different approaches
All Fireball Llama 8B models
Vision detection and scientific solution for plant disease
Quaints
Reasoning models
-
EpistemeAI/ReasoningCore-1B-T1
Text Generation • 1B • Updated • 1 -
EpistemeAI/ReasoningCore-3B-T1_1
Text Generation • 3B • Updated • 6 • 1 -
EpistemeAI/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO
Text Generation • 3B • Updated -
EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO
Text Generation • 8B • Updated • 7
EpistemeAI's fine-tune Gemma 2 9B gguf
Collections of Fireball-12B
Powerful Vibe coding LLM
Vision detection and scientific solution for plant disease
Hercules Gemma 3N collection
Quaints
These LLM are aligned and safe AI assistant
-
EpistemeAI/ReasoningCore-Llama-3B-R1-aligned
Text Generation • Updated • 2 • 1 -
EpistemeAI/SAI-DeepCoder-14B-Preview-v1.0
Text Generation • 15B • Updated • 6 -
EpistemeAI/SADeepCoder-1.5B-Preview-v1
Text Generation • 2B • Updated • 2 -
EpistemeAI/SAI-DeepMathCoder-14B-Preview-v1.0
Text Generation • 15B • Updated • 5 • 1
Reasoning models
-
EpistemeAI/ReasoningCore-1B-T1
Text Generation • 1B • Updated • 1 -
EpistemeAI/ReasoningCore-3B-T1_1
Text Generation • 3B • Updated • 6 • 1 -
EpistemeAI/Reasoning-Llama-3.2-3B-Math-Instruct-RE1-ORPO
Text Generation • 3B • Updated -
EpistemeAI/Reasoning-Llama-3.1-CoT-RE1-NMT-V2-ORPO
Text Generation • 8B • Updated • 7
Why limit AGI to one “super brain” when you can have multiple minds in one?
Psyche of Logic, Psyche of Emotion, Psyche of Improv .
-
EpistemeAI/Polypsyche-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto-divergent
Text Generation • 8B • Updated -
EpistemeAI/Polypsyche-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto-Logic
Text Generation • 8B • Updated • 1 -
EpistemeAI/Polypsyche-Llama-3.1-8B-Instruct-Agent-0.003-128K-code-ds-auto-Empathy
Text Generation • 8B • Updated -
EpistemeAI/Polypsyche-Llama-3.1-8B-Instruct-Agent-0.0031-128K-code-ds-auto-Logic
Text Generation • Updated • 1
Open fine-tuned Gemma, codegemma-2-9b
EpistemeAI's fine-tune Gemma 2 9B gguf
Fine-tuned Llama 3.1 with different approaches
Collections of Fireball-12B
All Fireball Llama 8B models