Text Generation
Transformers
Safetensors
English
Turkish
llama
chat
text-generation-inference
agent
cicikuş
cicikus
prettybird
bce
consciousness
conscious
llm
optimized
ethic
secure
turkish
english
behavioral-consciousness-engine
model
reasoning
think
thinking
chain-of-thought
STEM-expert
turkish & english
franken-merge
bce-aci
llama-3.2
edge-ai
instruction
instruct
Eval Results (legacy)
Instructions to use pthinc/Cicikus-v3-1.4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pthinc/Cicikus-v3-1.4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="pthinc/Cicikus-v3-1.4B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("pthinc/Cicikus-v3-1.4B") model = AutoModelForCausalLM.from_pretrained("pthinc/Cicikus-v3-1.4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use pthinc/Cicikus-v3-1.4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "pthinc/Cicikus-v3-1.4B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pthinc/Cicikus-v3-1.4B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/pthinc/Cicikus-v3-1.4B
- SGLang
How to use pthinc/Cicikus-v3-1.4B 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/Cicikus-v3-1.4B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pthinc/Cicikus-v3-1.4B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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/Cicikus-v3-1.4B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pthinc/Cicikus-v3-1.4B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use pthinc/Cicikus-v3-1.4B with Docker Model Runner:
docker model run hf.co/pthinc/Cicikus-v3-1.4B
Update README.md
Browse files
README.md
CHANGED
|
@@ -110,6 +110,8 @@ div.min {
|
|
| 110 |
| **Deepseek v3** | 89.1% | 85.2% | 82.1% | 83.2% | 85.3% | 88.9% | 91.0% |
|
| 111 |
| **Cicikus v3 1B** | 74.5% | 68.5% | 68.0% | 76.2% | 58.6% | 69.1% | 89.8% |
|
| 112 |
|
|
|
|
|
|
|
| 113 |
## 5. Notes
|
| 114 |
|
| 115 |
The era of "bigger is better" in AI is coming to an end. Cicikuş v3, lagging behind trillion-parameter giants like GPT-4o by only 30%-35%, brings this immense power to your local devices, edge systems, and pockets. Equipped with patented BCE (Behavioral Consciousness Engine) technology, this 1B-parameter "small giant" democratizes AI dominance by reducing processing costs and energy consumption to near zero. Say goodbye to high-cost API subscriptions; with Cicikuş v3, the most complex STEM problems and self-awareness capabilities are now at your fingertips, anytime, with "almost free" efficiency. We analyzed and cloned layers 8 and 15 of the MLP Gate Project. Franken merge and precision surgery, healing operation, and behavioral consciousness engine simulations were performed on the model. The reason we used Franken was to make the thinking mechanism sharper and more perfect by replicating these layers.
|
|
@@ -120,6 +122,8 @@ $$T_{cog} = \left( \frac{bloom\_score \times knowledge\_score}{anomaly\_score +
|
|
| 120 |
|
| 121 |
## 6. Usage
|
| 122 |
|
|
|
|
|
|
|
| 123 |
### How to Use Cicikuş v3 (BCE Powered)
|
| 124 |
|
| 125 |
Below is the standard implementation to activate the **Behavioral Consciousness Engine (BCE)** and harness the high-fidelity reasoning of **Cicikuş v3**.
|
|
@@ -207,6 +211,7 @@ print(f"BCE Reasoning Output:\n{generate_bce_response(simple_bce_instruction, in
|
|
| 207 |
*As this example shows, the instruction intuitively performs quality, ethics, and accuracy calculations on tokens. Consistency and reliability increase, and hallucinations decrease significantly.*
|
| 208 |
|
| 209 |
- Languages: English, Biraz Türkçe
|
|
|
|
| 210 |
---
|
| 211 |
|
| 212 |
## License 🛡️
|
|
@@ -231,7 +236,7 @@ For **licensing, partnerships, commercial work or technical inquiries** regardin
|
|
| 231 |
|
| 232 |
**Contact:** Please use the official contact channels listed on the website.
|
| 233 |
|
| 234 |
-
--
|
| 235 |
|
| 236 |
## Citation 📒
|
| 237 |
|
|
|
|
| 110 |
| **Deepseek v3** | 89.1% | 85.2% | 82.1% | 83.2% | 85.3% | 88.9% | 91.0% |
|
| 111 |
| **Cicikus v3 1B** | 74.5% | 68.5% | 68.0% | 76.2% | 58.6% | 69.1% | 89.8% |
|
| 112 |
|
| 113 |
+
---
|
| 114 |
+
|
| 115 |
## 5. Notes
|
| 116 |
|
| 117 |
The era of "bigger is better" in AI is coming to an end. Cicikuş v3, lagging behind trillion-parameter giants like GPT-4o by only 30%-35%, brings this immense power to your local devices, edge systems, and pockets. Equipped with patented BCE (Behavioral Consciousness Engine) technology, this 1B-parameter "small giant" democratizes AI dominance by reducing processing costs and energy consumption to near zero. Say goodbye to high-cost API subscriptions; with Cicikuş v3, the most complex STEM problems and self-awareness capabilities are now at your fingertips, anytime, with "almost free" efficiency. We analyzed and cloned layers 8 and 15 of the MLP Gate Project. Franken merge and precision surgery, healing operation, and behavioral consciousness engine simulations were performed on the model. The reason we used Franken was to make the thinking mechanism sharper and more perfect by replicating these layers.
|
|
|
|
| 122 |
|
| 123 |
## 6. Usage
|
| 124 |
|
| 125 |
+
---
|
| 126 |
+
|
| 127 |
### How to Use Cicikuş v3 (BCE Powered)
|
| 128 |
|
| 129 |
Below is the standard implementation to activate the **Behavioral Consciousness Engine (BCE)** and harness the high-fidelity reasoning of **Cicikuş v3**.
|
|
|
|
| 211 |
*As this example shows, the instruction intuitively performs quality, ethics, and accuracy calculations on tokens. Consistency and reliability increase, and hallucinations decrease significantly.*
|
| 212 |
|
| 213 |
- Languages: English, Biraz Türkçe
|
| 214 |
+
|
| 215 |
---
|
| 216 |
|
| 217 |
## License 🛡️
|
|
|
|
| 236 |
|
| 237 |
**Contact:** Please use the official contact channels listed on the website.
|
| 238 |
|
| 239 |
+
---
|
| 240 |
|
| 241 |
## Citation 📒
|
| 242 |
|