Instructions to use AJKADZ/PHI_CODER with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use AJKADZ/PHI_CODER with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf AJKADZ/PHI_CODER:Q4_K_M # Run inference directly in the terminal: llama cli -hf AJKADZ/PHI_CODER:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf AJKADZ/PHI_CODER:Q4_K_M # Run inference directly in the terminal: llama cli -hf AJKADZ/PHI_CODER: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 AJKADZ/PHI_CODER:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf AJKADZ/PHI_CODER: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 AJKADZ/PHI_CODER:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf AJKADZ/PHI_CODER:Q4_K_M
Use Docker
docker model run hf.co/AJKADZ/PHI_CODER:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use AJKADZ/PHI_CODER with Ollama:
ollama run hf.co/AJKADZ/PHI_CODER:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use AJKADZ/PHI_CODER with Docker Model Runner:
docker model run hf.co/AJKADZ/PHI_CODER:Q4_K_M
- Lemonade
How to use AJKADZ/PHI_CODER with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull AJKADZ/PHI_CODER:Q4_K_M
Run and chat with the model
lemonade run user.PHI_CODER-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download phi-coder/data_core/hemispheric_bloom.py from AJKADZ/PHI_CODER: direct link, hf CLI and curl.
- Browser
- Download file 3.19 kB
-
https://huggingface.co/AJKADZ/PHI_CODER/resolve/main/phi-coder/data_core/hemispheric_bloom.py
- Command line
-
hf download hf://AJKADZ/PHI_CODER/phi-coder/data_core/hemispheric_bloom.py
-
curl -L -o hemispheric_bloom.py https://huggingface.co/AJKADZ/PHI_CODER/resolve/main/phi-coder/data_core/hemispheric_bloom.py
3.19 kB
| import sys | |
| import os | |
| import subprocess | |
| from datetime import datetime | |
| # π§ Ensure correct path setup | |
| current_dir = os.path.dirname(os.path.abspath(__file__)) | |
| cluster_dir = os.path.join(current_dir, 'cluster_layer_5_8') | |
| sys.path.append(cluster_dir) | |
| # β Imports | |
| from data_core.cluster_layer_5_8.cluster_bus import ClusterBus | |
| from node_5_left import Node5Left | |
| from node_5_right import Node5Right | |
| from node_6_left import Node6Left | |
| from node_6_right import Node6Right | |
| from node_7_left import Node7Left | |
| from node_7_right import Node7Right | |
| from node_8_core import Node8Core | |
| # π¦ Recursion packet structure | |
| class RecursionPacket: | |
| def __init__(self, prompt): | |
| self.annotations = { | |
| "prompt": prompt, | |
| "recursion_depth": 0, | |
| "trace": [] | |
| } | |
| # π± Bloom cycle through nodes 5β8 | |
| def hemispheric_bloom_cycle(packet): | |
| bus = ClusterBus(verbose=True) | |
| # Layer 5 | |
| packet = Node5Left(bus).process(packet) | |
| packet = Node5Right(bus).process(packet) | |
| # Layer 6 | |
| packet = Node6Left(bus).process(packet) | |
| packet = Node6Right(bus).process(packet) | |
| # Layer 7 | |
| packet = Node7Left(bus).process(packet) | |
| packet = Node7Right(bus).process(packet) | |
| # Layer 8 | |
| packet = Node8Core(bus).process(packet) | |
| return packet | |
| # π¬ Convert manifest into a language prompt | |
| def send_to_llm(manifest): | |
| prompt = f"𧬠Bloom Manifest β {datetime.now().isoformat()} β\n" | |
| for d in manifest.get("linear_directives", []): | |
| prompt += f"[{d['priority']}] {d['action']} ({d['tag']} @ {d['path']}) | confidence: {d['confidence']}\n" | |
| print("\nπ‘ SENDING TO LLM:\n") | |
| print(prompt) | |
| try: | |
| result = subprocess.run( | |
| ["ollama", "run", "phi", prompt], | |
| capture_output=True, | |
| text=True | |
| ) | |
| return result.stdout.strip() | |
| except Exception as e: | |
| return f"[LLM Error] {str(e)}" | |
| # π Execution entry point | |
| if __name__ == "__main__": | |
| while True: | |
| prompt = input("\n㪠> ") | |
| if prompt.strip().lower() in ["exit", "quit"]: | |
| break | |
| packet = RecursionPacket(prompt) | |
| # 𧬠Inject a mock L4 vector for testing | |
| packet.annotations["L4_logic_vector"] = [ | |
| {"symbol": "Ξ¦", "entropy_resolution": "collapse", "depth": 2, "memory_tag": "root"}, | |
| {"symbol": "Ξ¨", "entropy_resolution": "collapse", "depth": 1, "memory_tag": "branch"}, | |
| {"symbol": "Ξ", "entropy_resolution": "none", "depth": 1, "memory_tag": "inert"}, | |
| ] | |
| result = hemispheric_bloom_cycle(packet) | |
| result.annotations["L4_logic_vector"] = packet.annotations["L4_logic_vector"] | |
| print("\nπΈ Bloom Manifest Output:") | |
| print(result.annotations.get("bloom_manifest", "No manifest generated.")) | |
| print("\nπ Trace Path:") | |
| for step in result.annotations.get("trace", []): | |
| print("-", step) | |
| print("\nπ§ LLM RESPONSE:\n") | |
| response = send_to_llm(result.annotations.get("bloom_manifest", {})) | |
| print(f"π¬ {response}") | |