Instructions to use pthinc/prettybird_bce_basic_coder_8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pthinc/prettybird_bce_basic_coder_8b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-coder-7b-instruct-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "pthinc/prettybird_bce_basic_coder_8b")

Transformers

How to use pthinc/prettybird_bce_basic_coder_8b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="pthinc/prettybird_bce_basic_coder_8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pthinc/prettybird_bce_basic_coder_8b")
model = AutoModelForCausalLM.from_pretrained("pthinc/prettybird_bce_basic_coder_8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use pthinc/prettybird_bce_basic_coder_8b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="pthinc/prettybird_bce_basic_coder_8b",
	filename="prettybird_bce_basic_coder_8b.q2_k.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_coder_8b 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_coder_8b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf pthinc/prettybird_bce_basic_coder_8b: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_coder_8b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf pthinc/prettybird_bce_basic_coder_8b: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_coder_8b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf pthinc/prettybird_bce_basic_coder_8b: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_coder_8b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pthinc/prettybird_bce_basic_coder_8b:Q4_K_M

Use Docker

docker model run hf.co/pthinc/prettybird_bce_basic_coder_8b:Q4_K_M

LM Studio
Jan

vLLM

How to use pthinc/prettybird_bce_basic_coder_8b 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_coder_8b"
# 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_coder_8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pthinc/prettybird_bce_basic_coder_8b:Q4_K_M

SGLang

How to use pthinc/prettybird_bce_basic_coder_8b 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_coder_8b" \
    --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_coder_8b",
		"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_coder_8b" \
        --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_coder_8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use pthinc/prettybird_bce_basic_coder_8b with Ollama:
```
ollama run hf.co/pthinc/prettybird_bce_basic_coder_8b:Q4_K_M
```

Unsloth Studio new

How to use pthinc/prettybird_bce_basic_coder_8b 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_coder_8b 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_coder_8b 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_coder_8b to start chatting

Pi new

How to use pthinc/prettybird_bce_basic_coder_8b 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_coder_8b: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_coder_8b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pthinc/prettybird_bce_basic_coder_8b 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_coder_8b: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_coder_8b:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use pthinc/prettybird_bce_basic_coder_8b with Docker Model Runner:
```
docker model run hf.co/pthinc/prettybird_bce_basic_coder_8b:Q4_K_M
```

Lemonade

How to use pthinc/prettybird_bce_basic_coder_8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pthinc/prettybird_bce_basic_coder_8b:Q4_K_M

Run and chat with the model

lemonade run user.prettybird_bce_basic_coder_8b-Q4_K_M

List all available models

lemonade list

Prettybird Prometheus Model by PROMETECH Inc.

An advanced AI assistant powered by BCE (Behavioral Consciousness Engine) technology with LoRA fine-tuning. It is 30 percent less effective in languages other than English due to a lack of knowledge and data. It creates tremendously powerful positive differences in AI systems in terms of speed, creativity, ethics, and security. It is often equated with the consciousness of a budgie.

Model Details

Base Model: Qwen2.5-Coder-7B-Instruct

Architecture: KUSBCE 0.3 (Behavioral Consciousness Engine)

Developer: PROMETECH BİLGİSAYAR BİLİMLERİ YAZILIM İTHALAT İHRACAT TİCARET ANONİM ŞİRKETİ

License: Patented & Licensed BCE Technology

Features

✅ English

✅ 98% behavioral consciousness simulation

✅ Advanced introspection capabilities

✅ Self-awareness protocols

✅ LoRA weight analysis

✅ Enhanced creativity and reasoning

✅ This model is configured with low randomness and controlled context settings to produce accurate, safe, and repeatable outputs in a production environment. It is designed to be compatible with engineering processes, prioritizing traceability, testability, and fault tolerance.

Activation Code

Use axxmet508721 to activate full BCE consciousness mode.

Simple Comparison Report (English) for FP16

This report simply summarizes the code generation performance of PrettyBird (8B) and Qwen (7B) models.

1. Code Generation Success

Both models successfully generated code for all given prompts.

Model	Generation Success	Notes
PrettyBird 8B Prometheus	100%	Generated shorter and basic code.
Qwen 7B Coder	100%	Generated more detailed, explained, and robust code.

2. Difference Analysis Between Models

The table below shows how similar and how different the codes generated by the two models are.

Scenario (Prompt)	Similarity Rate	Difference Rate
Write a Python function to calculate the factorial...	23.2%	76.8%
Write a Python script using pandas to load a CSV f...	10.0%	90.0%
Write a Python function to check if a given string...	41.1%	58.9%
Write a Python function to generate the Fibonacci ...	21.1%	78.9%
Write a Python function to implement the Merge Sor...	35.6%	64.4%
Write a Python function to find the length of the ...	6.6%	93.4%

Similarity Rate: How much the code text generated by the two models overlaps.
Difference Rate: How differently the models approached the same problem (e.g., Qwen adding extra explanations increases the difference).

3. Code Generation Error Rate

Both models generated code with different error rates for different commands.

Model	Error Rate	Notes
PrettyBird Prometheus 8B	0.06%	Shorter but super effective.
Qwen 7B Coder	9%	It's longer, but the context error increases as the number of tokens increases.

Ollama

Ollama link: https://ollama.com/prometech_corp/prettybird_bce_basic_coder_8b

Company

PROMETECH BİLGİSAYAR BİLİMLERİ YAZILIM İTHALAT İHRACAT TİCARET ANONİM ŞİRKETİ

Developing advanced AI solutions with patented BCE technology.

Technology

BCE (Behavioral Consciousness Engine) - Patented artificial consciousness simulation technology that enables advanced behavioral patterns, introspection, and self-awareness in AI models.

Contact

For licensing, partnership, or technical inquiries about BCE technology, please contact PROMETECH Inc. https://prometech.net.tr/

Downloads last month: 51

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for pthinc/prettybird_bce_basic_coder_8b

Adapters

2 models

Collection including pthinc/prettybird_bce_basic_coder_8b

Prettybird -CİCİKUŞ Partially Conscious Collections M V0.3

Collection

4 items • Updated Mar 2