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/ggml/src/ggml-cpu/hbm.cpp from AJKADZ/PHI_CODER: direct link, hf CLI and curl.
- Browser
- Download file 2.06 kB
-
https://huggingface.co/AJKADZ/PHI_CODER/resolve/main/phi-coder-hf/llama.cpp/ggml/src/ggml-cpu/hbm.cpp
- Command line
-
hf download hf://AJKADZ/PHI_CODER/phi-coder-hf/llama.cpp/ggml/src/ggml-cpu/hbm.cpp
-
curl -L -o hbm.cpp https://huggingface.co/AJKADZ/PHI_CODER/resolve/main/phi-coder-hf/llama.cpp/ggml/src/ggml-cpu/hbm.cpp
2.06 kB
| // buffer type HBM | |
| static const char * ggml_backend_cpu_hbm_buffer_type_get_name(ggml_backend_buffer_type_t buft) { | |
| return "CPU_HBM"; | |
| GGML_UNUSED(buft); | |
| } | |
| static void ggml_backend_cpu_hbm_buffer_free_buffer(ggml_backend_buffer_t buffer) { | |
| hbw_free(buffer->context); | |
| } | |
| static ggml_backend_buffer_t ggml_backend_cpu_hbm_buffer_type_alloc_buffer(ggml_backend_buffer_type_t buft, | |
| size_t size) { | |
| void * ptr; | |
| int result = hbw_posix_memalign(&ptr, ggml_backend_cpu_buffer_type_get_alignment(buft), size); | |
| if (result != 0) { | |
| GGML_LOG_ERROR("failed to allocate HBM buffer of size %zu\n", size); | |
| return NULL; | |
| } | |
| ggml_backend_buffer_t buffer = ggml_backend_cpu_buffer_from_ptr(ptr, size); | |
| buffer->buft = buft; | |
| buffer->iface.free_buffer = ggml_backend_cpu_hbm_buffer_free_buffer; | |
| return buffer; | |
| } | |
| ggml_backend_buffer_type_t ggml_backend_cpu_hbm_buffer_type(void) { | |
| static struct ggml_backend_buffer_type ggml_backend_cpu_buffer_type_hbm = { | |
| /* .iface = */ { | |
| /* .get_name = */ ggml_backend_cpu_hbm_buffer_type_get_name, | |
| /* .alloc_buffer = */ ggml_backend_cpu_hbm_buffer_type_alloc_buffer, | |
| /* .get_alignment = */ ggml_backend_cpu_buffer_type_get_alignment, | |
| /* .get_max_size = */ nullptr, // defaults to SIZE_MAX | |
| /* .get_alloc_size = */ nullptr, // defaults to ggml_nbytes | |
| /* .is_host = */ ggml_backend_cpu_buffer_type_is_host, | |
| }, | |
| /* .context = */ nullptr, | |
| }; | |
| return &ggml_backend_cpu_buffer_type_hbm; | |
| } | |