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-hf/llama.cpp/tools/server/tests/unit/test_tokenize.py from AJKADZ/PHI_CODER: direct link, hf CLI and curl.
- Browser
- Download file 1.64 kB
-
https://huggingface.co/AJKADZ/PHI_CODER/resolve/main/phi-coder-hf/llama.cpp/tools/server/tests/unit/test_tokenize.py
- Command line
-
hf download hf://AJKADZ/PHI_CODER/phi-coder-hf/llama.cpp/tools/server/tests/unit/test_tokenize.py
-
curl -L -o test_tokenize.py https://huggingface.co/AJKADZ/PHI_CODER/resolve/main/phi-coder-hf/llama.cpp/tools/server/tests/unit/test_tokenize.py
1.64 kB
| import pytest | |
| from utils import * | |
| server = ServerPreset.tinyllama2() | |
| def create_server(): | |
| global server | |
| server = ServerPreset.tinyllama2() | |
| def test_tokenize_detokenize(): | |
| global server | |
| server.start() | |
| # tokenize | |
| content = "What is the capital of France ?" | |
| res_tok = server.make_request("POST", "/tokenize", data={ | |
| "content": content | |
| }) | |
| assert res_tok.status_code == 200 | |
| assert len(res_tok.body["tokens"]) > 5 | |
| # detokenize | |
| res_detok = server.make_request("POST", "/detokenize", data={ | |
| "tokens": res_tok.body["tokens"], | |
| }) | |
| assert res_detok.status_code == 200 | |
| assert res_detok.body["content"].strip() == content | |
| def test_tokenize_with_bos(): | |
| global server | |
| server.start() | |
| # tokenize | |
| content = "What is the capital of France ?" | |
| bosId = 1 | |
| res_tok = server.make_request("POST", "/tokenize", data={ | |
| "content": content, | |
| "add_special": True, | |
| }) | |
| assert res_tok.status_code == 200 | |
| assert res_tok.body["tokens"][0] == bosId | |
| def test_tokenize_with_pieces(): | |
| global server | |
| server.start() | |
| # tokenize | |
| content = "This is a test string with unicode 媽 and emoji 🤗" | |
| res_tok = server.make_request("POST", "/tokenize", data={ | |
| "content": content, | |
| "with_pieces": True, | |
| }) | |
| assert res_tok.status_code == 200 | |
| for token in res_tok.body["tokens"]: | |
| assert "id" in token | |
| assert token["id"] > 0 | |
| assert "piece" in token | |
| assert len(token["piece"]) > 0 | |