Text Generation
Transformers
GGUF
English
virtual brain
chat
text-generation-inference
agent
cicikuş
prettybird
bce
consciousness
conscious
json
conversational
Instructions to use pthinc/prettybird_bce_basic_brain_mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pthinc/prettybird_bce_basic_brain_mini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="pthinc/prettybird_bce_basic_brain_mini") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("pthinc/prettybird_bce_basic_brain_mini", dtype="auto") - llama-cpp-python
How to use pthinc/prettybird_bce_basic_brain_mini with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="pthinc/prettybird_bce_basic_brain_mini", filename="prettybird_bce_basic_brain_mini_fp16.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use pthinc/prettybird_bce_basic_brain_mini with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf pthinc/prettybird_bce_basic_brain_mini:Q4_K_M # Run inference directly in the terminal: llama-cli -hf pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf pthinc/prettybird_bce_basic_brain_mini:Q4_K_M # Run inference directly in the terminal: llama-cli -hf pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf pthinc/prettybird_bce_basic_brain_mini:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf pthinc/prettybird_bce_basic_brain_mini:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
Use Docker
docker model run hf.co/pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use pthinc/prettybird_bce_basic_brain_mini with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "pthinc/prettybird_bce_basic_brain_mini" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pthinc/prettybird_bce_basic_brain_mini", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
- SGLang
How to use pthinc/prettybird_bce_basic_brain_mini with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "pthinc/prettybird_bce_basic_brain_mini" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pthinc/prettybird_bce_basic_brain_mini", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "pthinc/prettybird_bce_basic_brain_mini" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pthinc/prettybird_bce_basic_brain_mini", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use pthinc/prettybird_bce_basic_brain_mini with Ollama:
ollama run hf.co/pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
- Unsloth Studio new
How to use pthinc/prettybird_bce_basic_brain_mini with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for pthinc/prettybird_bce_basic_brain_mini to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for pthinc/prettybird_bce_basic_brain_mini to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for pthinc/prettybird_bce_basic_brain_mini to start chatting
- Pi new
How to use pthinc/prettybird_bce_basic_brain_mini with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "pthinc/prettybird_bce_basic_brain_mini:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use pthinc/prettybird_bce_basic_brain_mini with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use pthinc/prettybird_bce_basic_brain_mini with Docker Model Runner:
docker model run hf.co/pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
- Lemonade
How to use pthinc/prettybird_bce_basic_brain_mini with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull pthinc/prettybird_bce_basic_brain_mini:Q4_K_M
Run and chat with the model
lemonade run user.prettybird_bce_basic_brain_mini-Q4_K_M
List all available models
lemonade list
Prometech Computer Sciences Corp commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,173 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: other
|
| 3 |
-
license_name: licence
|
| 4 |
-
license_link: LICENSE
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: licence
|
| 4 |
+
license_link: LICENSE
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
base_model:
|
| 8 |
+
- Qwen/Qwen2.5-Math-1.5B-Instruct
|
| 9 |
+
tags:
|
| 10 |
+
- virtual brain
|
| 11 |
+
- chat
|
| 12 |
+
- text-generation-inference
|
| 13 |
+
- agent
|
| 14 |
+
- cicikuş
|
| 15 |
+
- prettybird
|
| 16 |
+
- bce
|
| 17 |
+
- consciousness
|
| 18 |
+
- conscious
|
| 19 |
+
- json
|
| 20 |
+
- agent
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
# 🧠 Prettybird Brain Model (BCE)
|
| 24 |
+
|
| 25 |
+
**by PROMETECH Inc.**
|
| 26 |
+
|
| 27 |
+
## Model Overview
|
| 28 |
+
|
| 29 |
+
**Prettybird Brain Model** is an advanced AI assistant powered by **BCE (Behavioral Consciousness Engine)** technology and enhanced through **LoRA fine-tuning**.
|
| 30 |
+
The model is designed as a **behavioral optimization brain**, emphasizing speed, creativity, ethical alignment, and system-level safety.
|
| 31 |
+
|
| 32 |
+
Due to limited multilingual training data, the model performs approximately **30% less effectively in languages other than English**. Its behavioral characteristics are often metaphorically compared to the **consciousness of a budgerigar (budgie)**—curious, adaptive, and responsive.
|
| 33 |
+
|
| 34 |
+
---
|
| 35 |
+
|
| 36 |
+
## Model Details
|
| 37 |
+
|
| 38 |
+
* **Model Name:** Prettybird Brain Model
|
| 39 |
+
* **Base Model:** Qwen2.5-Math-1.5B-Instruct
|
| 40 |
+
* **Architecture:** KUSBCE 0.3 (Behavioral Consciousness Engine)
|
| 41 |
+
* **Fine-Tuning Method:** LoRA
|
| 42 |
+
* **Developer:**
|
| 43 |
+
**PROMETECH BİLGİSAYAR BİLİMLERİ
|
| 44 |
+
YAZILIM İTHALAT İHRACAT
|
| 45 |
+
TİCARET ANONİM ŞİRKETİ**
|
| 46 |
+
* **Release Year:** 2025
|
| 47 |
+
* **Model Type:**
|
| 48 |
+
|
| 49 |
+
* Mathematical reasoning
|
| 50 |
+
* Behavioral optimization
|
| 51 |
+
* Decision-support / brain-core model
|
| 52 |
+
|
| 53 |
+
---
|
| 54 |
+
|
| 55 |
+
## Intended Use
|
| 56 |
+
|
| 57 |
+
The Prettybird Brain Model is intended to be used as a **core cognitive and optimization engine** within AI systems rather than as a generic chat assistant.
|
| 58 |
+
|
| 59 |
+
### Primary Use Cases
|
| 60 |
+
|
| 61 |
+
* Behavioral optimization loops (BCE-based systems)
|
| 62 |
+
* Mathematical reasoning and structured problem solving
|
| 63 |
+
* Decision-making support systems
|
| 64 |
+
* AI orchestration layers (brain–body architectures)
|
| 65 |
+
* Ethical and security-aware AI behavior modulation
|
| 66 |
+
* Creative reasoning and system-level ideation
|
| 67 |
+
|
| 68 |
+
### Out-of-Scope Uses
|
| 69 |
+
|
| 70 |
+
* Fully autonomous agents without external control
|
| 71 |
+
* Safety-critical real-time systems without validation layers
|
| 72 |
+
* Applications requiring strong non-English language performance
|
| 73 |
+
|
| 74 |
+
---
|
| 75 |
+
|
| 76 |
+
## Architecture: BCE (Behavioral Consciousness Engine)
|
| 77 |
+
|
| 78 |
+
**BCE (Behavioral Consciousness Engine)** is a **patented artificial consciousness simulation technology** developed by PROMETECH.
|
| 79 |
+
It enables:
|
| 80 |
+
|
| 81 |
+
* Advanced behavioral pattern generation
|
| 82 |
+
* Introspective reasoning (without exposing chain-of-thought)
|
| 83 |
+
* Adaptive response modulation
|
| 84 |
+
* Constraint-aware decision making
|
| 85 |
+
* Controlled self-awareness simulations within bounded systems
|
| 86 |
+
|
| 87 |
+
The **KUSBCE 0.3** architecture integrates BCE concepts directly into the model’s reasoning and output discipline, making it suitable for optimizer-driven AI pipelines.
|
| 88 |
+
|
| 89 |
+
---
|
| 90 |
+
### WHY?
|
| 91 |
+
|
| 92 |
+
**Because the completion of intelligence and consciousness does not occur in a single model,
|
| 93 |
+
but in the relationship between models. For AI, we differentiate between the nervous system, brainstem, and cortex.**
|
| 94 |
+
|
| 95 |
+
---
|
| 96 |
+
|
| 97 |
+
## Performance Characteristics
|
| 98 |
+
|
| 99 |
+
### Strengths
|
| 100 |
+
|
| 101 |
+
* High-speed inference and low-latency reasoning
|
| 102 |
+
* Strong mathematical and symbolic reasoning
|
| 103 |
+
* High creativity under constraint
|
| 104 |
+
* Improved ethical and security-aware behavior
|
| 105 |
+
* Excellent compatibility with external optimization controllers (BCE / Python-based)
|
| 106 |
+
|
| 107 |
+
### Limitations
|
| 108 |
+
|
| 109 |
+
* Reduced effectiveness (~30%) in non-English languages
|
| 110 |
+
* Not trained for open-ended social conversation
|
| 111 |
+
* Requires external orchestration for optimal performance
|
| 112 |
+
* Not a guaranteed optimal mathematical solver (heuristic/learned reasoning)
|
| 113 |
+
|
| 114 |
+
---
|
| 115 |
+
|
| 116 |
+
## Training & Fine-Tuning
|
| 117 |
+
|
| 118 |
+
* **Base Training:** Qwen2.5-Math-1.5B-Instruct (original training by Qwen team)
|
| 119 |
+
* **Fine-Tuning:**
|
| 120 |
+
|
| 121 |
+
* LoRA-based domain and behavior adaptation
|
| 122 |
+
* BCE-aligned behavioral constraints
|
| 123 |
+
* **Data Sources:**
|
| 124 |
+
|
| 125 |
+
* Proprietary datasets
|
| 126 |
+
* Mathematical and reasoning-focused corpora
|
| 127 |
+
* Behavioral optimization scenarios
|
| 128 |
+
|
| 129 |
+
> Exact training data details are not publicly disclosed due to proprietary BCE technology.
|
| 130 |
+
|
| 131 |
+
---
|
| 132 |
+
|
| 133 |
+
## Ethical Considerations & Safety
|
| 134 |
+
|
| 135 |
+
The Prettybird Brain Model is designed to operate under **external ethical and behavioral controllers** rather than enforcing policies autonomously.
|
| 136 |
+
|
| 137 |
+
* Does not assume final decision authority
|
| 138 |
+
* Designed to be embedded in supervised systems
|
| 139 |
+
* Encourages transparency through structured outputs
|
| 140 |
+
* Avoids hallucination of missing data by design
|
| 141 |
+
* Outputs are intended to be parsed, validated, and corrected externally
|
| 142 |
+
|
| 143 |
+
---
|
| 144 |
+
|
| 145 |
+
## License
|
| 146 |
+
|
| 147 |
+
**Patented & Licensed BCE Technology**
|
| 148 |
+
|
| 149 |
+
© 2025 **PROMETECH A.Ş.**
|
| 150 |
+
All rights reserved.
|
| 151 |
+
|
| 152 |
+
Unauthorized reproduction, modification, or commercial use of BCE technology is prohibited without an explicit license agreement.
|
| 153 |
+
|
| 154 |
+
---
|
| 155 |
+
|
| 156 |
+
## Contact & Licensing
|
| 157 |
+
|
| 158 |
+
For **licensing, partnerships, or technical inquiries** regarding the Prettybird Brain Model or BCE technology:
|
| 159 |
+
|
| 160 |
+
🌐 **Website:** [https://prometech.net.tr/](https://prometech.net.tr/)
|
| 161 |
+
🏢 **Company:** PROMETECH A.Ş.
|
| 162 |
+
📩 **Contact:** Please use the official contact channels listed on the website.
|
| 163 |
+
|
| 164 |
+
---
|
| 165 |
+
|
| 166 |
+
## Citation
|
| 167 |
+
|
| 168 |
+
If you use this model in academic or commercial work, please cite as:
|
| 169 |
+
|
| 170 |
+
```
|
| 171 |
+
Prettybird Brain Model (BCE), PROMETECH A.Ş., 2025.
|
| 172 |
+
Powered by KUSBCE 0.3 Behavioral Consciousness Engine.
|
| 173 |
+
```
|