---
license: other
license_name: iconn
license_link: LICENSE
library_name: transformers
tags:
- emotional-ai
- ICONN
- chatbot
- base
co2_eq_emissions:
  emissions: 2.74
  source: CodeCarbon
  training_type: pretraining
  geographical_location: US-West
  hardware_used: 18 x B200
extra_gated_prompt: >
  By accessing or downloading this model, you agree to the ICONN AI License
  Agreement.  This includes restrictions on commercial use, redistribution,
  derivative model training,  and uploading to public or private repositories.
  You may not use this model to harm, surveil,  deceive, exploit, manipulate, or
  conduct unethical AI research. All use must comply with  ethical standards and
  respect human dignity.
extra_gated_fields:
  Full name: text
  Organization (if any): text
  Country: country
  Date of agreement: date_picker
  I am using this model for:
    type: select
    options:
    - Personal use
    - Internal business use
    - Academic research
    - Educational purposes
    - label: Other (explain below)
      value: other
  Purpose explanation (if "Other"): text
  I agree to all terms in the ICONN AI License Agreement, including:
    type: checkbox
    options:
    - >-
      I will NOT use this model for commercial purposes without explicit written
      permission.
    - >-
      I will NOT redistribute, upload, or share this model in any public or
      private repository.
    - I will NOT train new models or derivatives from this model.
    - >-
      I will NOT use this model for unethical, harmful, deceptive, exploitative,
      or surveillance purposes.
    - I understand this license may be revoked if I breach any terms.
pipeline_tag: text-generation
---

# ICONN e1: The new era of Open-Source CoT in AI

**GPU poor? Less than 3x A100s? A e1 Lite model is coming with just 22B parameters alongside a model for consumer CPUs with 14B and 7B parameters.


-   **Emotional Context Awareness**  
    ICONN e1 interprets emotional cues and adjusts tone, vocabulary, and response style—offering a more human-like, emotionally reactive experience.
    
-   ** ICONN Emotional Core (IEC) (Notice: Not available on Huggingface)**  
    Powered by millions of small AI agents, IEC gives ICONN its emotional personality, with billions of simulated emotional states and detections.
    
-   **Reasoning**  
    ICONN e1 is one of the most powerful reasoning open-source models, and most closed-source models in or out of Huggingface.






# What is in the ICONN i1 MoE?





## ICONN i1 MoE and Experts

ICONN e1, being a MoE just like it's base model ICONN 1, has multiple expert models. Keywords are taken from the user's input to choose which expert generates the output.

| Expert Chosen       | User Input                                                                                                                                                                                                                                                                     |
|---------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| ICONN-e1            | `'Hi!'`                                                                                                                                                                                                                                                                         |
| ICONN-e1-Pro        | `Solve for m: m² − (2 + ∑₍ⱼ₌₁₎² j)·m + (1 + ∑₍ⱼ₌₁₎³ j² − 14) = 0.`                                                                                                                                                                        |
| ICONN-e1-Science    | `If a stable isotope of Ununoctium (Uuo, now Og) could be synthesized in bulk, what would be its most likely physical state at STP and why, considering relativistic effects?`                                                                                                |
| ICONN-e1-Code       | `Create a zero-dependency quantum-safe VM in Zig that compiles a domain-specific language into a fully homomorphic encrypted IR, supports hot-reloading WebAssembly modules, parallel scheduling via lock-free fibers, and performs live introspection through a headless OpenGL debug overlay.` |

**ICONN-e1:**  
ICONN's general-purpose reasoning model, designed for everyday tasks, logic, and conversation.

**ICONN-e1-Pro:**  
ICONN's advanced reasoning model, optimized for complex problem-solving in math, logic, and professional domains.

**ICONN-e1-Science:**  
ICONN's scientific expert model, trained on advanced science datasets to enhance precision in physics, chemistry, biology, and technical reasoning.

**ICONN-e1-Code:**  
ICONN's coding specialist, trained for programming, compiler theory, software architecture, and technical code generation across multiple languages.


# Usage
**First, make sure you have at least 4x Nvidia A100 or a single B100, and 120GB RAM and 120-192GB VRAM. Don't have this? Use our Lite model, coming soon.

> Run the code below to run ICONN i1:

```python
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
import torch

def run_iconn_chatbot(model_name="ICONNAI/ICONN-e1"):

    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name)
    
    device = 0 if torch.cuda.is_available() else -1
    
    chat_pipeline = pipeline(
        "text-generation",
        model=model,
        tokenizer=tokenizer,
        device=device,
        max_length=1624,
        do_sample=True,
        top_p=0.9,
        temperature=0.4,
        pad_token_id=tokenizer.eos_token_id
    )
    
    print(f"ICONN chatbot running with model: {model_name}. Type 'exit' to quit.")
    conversation_history = ""
    
    while True:
        user_input = input("You: ")
        if user_input.lower() == "exit":
            print("Goodbye!")
            break
        
        conversation_history += f"User: {user_input}\nBot:"
        
        response = chat_pipeline(conversation_history, max_length=len(tokenizer.encode(conversation_history)) + 100)[0]['generated_text']
        
        bot_reply = response[len(conversation_history):].strip().split("\n")[0]
        
        print(f"Bot: {bot_reply}")
        
        conversation_history += f" {bot_reply}\n"

if __name__ == "__main__":
    run_iconn_chatbot()
```