Safetensors
GGUF
Turkish
llama
Llama-3
instruct
finetune
chatml
gpt4
synthetic data
distillation
function calling
json mode
axolotl
roleplaying
chat
Instructions to use tda45/TdAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use tda45/TdAI with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="tda45/TdAI", filename="llama.cpp/models/ggml-vocab-aquila.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use tda45/TdAI 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 tda45/TdAI # Run inference directly in the terminal: llama cli -hf tda45/TdAI
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf tda45/TdAI # Run inference directly in the terminal: llama cli -hf tda45/TdAI
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 tda45/TdAI # Run inference directly in the terminal: ./llama-cli -hf tda45/TdAI
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 tda45/TdAI # Run inference directly in the terminal: ./build/bin/llama-cli -hf tda45/TdAI
Use Docker
docker model run hf.co/tda45/TdAI
- LM Studio
- Jan
- Ollama
How to use tda45/TdAI with Ollama:
ollama run hf.co/tda45/TdAI
- Unsloth Studio
How to use tda45/TdAI 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 tda45/TdAI 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 tda45/TdAI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for tda45/TdAI to start chatting
- Atomic Chat new
- Docker Model Runner
How to use tda45/TdAI with Docker Model Runner:
docker model run hf.co/tda45/TdAI
- Lemonade
How to use tda45/TdAI with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tda45/TdAI
Run and chat with the model
lemonade run user.TdAI-{{QUANT_TAG}}List all available models
lemonade list
| cmake_minimum_required(VERSION 3.13) | |
| find_package(Python3 REQUIRED) | |
| # Shader locations | |
| set(SHADER_DIR "${CMAKE_CURRENT_SOURCE_DIR}/wgsl-shaders") | |
| set(SHADER_OUTPUT_DIR "${CMAKE_CURRENT_BINARY_DIR}/generated") | |
| set(SHADER_HEADER "${SHADER_OUTPUT_DIR}/ggml-wgsl-shaders.hpp") | |
| file(MAKE_DIRECTORY ${SHADER_OUTPUT_DIR}) | |
| message(STATUS "Shader output dir: ${SHADER_OUTPUT_DIR}") | |
| # Find all WGSL sources | |
| file(GLOB WGSL_SHADER_FILES | |
| "${SHADER_DIR}/*.wgsl" | |
| "${SHADER_DIR}/*.tmpl" | |
| ) | |
| # Generate the header using a Python script | |
| add_custom_command( | |
| OUTPUT ${SHADER_HEADER} | |
| COMMAND ${CMAKE_COMMAND} -E echo "Embedding WGSL shaders to ggml-wgsl-shaders.hpp" | |
| COMMAND ${CMAKE_COMMAND} -E make_directory ${SHADER_OUTPUT_DIR} | |
| COMMAND ${CMAKE_COMMAND} -E env PYTHONIOENCODING=utf-8 | |
| ${Python3_EXECUTABLE} ${CMAKE_CURRENT_SOURCE_DIR}/wgsl-shaders/embed_wgsl.py | |
| --input_dir "${SHADER_DIR}" | |
| --output_file "${SHADER_HEADER}" | |
| DEPENDS ${WGSL_SHADER_FILES} ${CMAKE_CURRENT_SOURCE_DIR}/wgsl-shaders/embed_wgsl.py | |
| VERBATIM | |
| ) | |
| add_custom_target(generate_shaders DEPENDS ${SHADER_HEADER}) | |
| ggml_add_backend_library(ggml-webgpu | |
| ggml-webgpu.cpp | |
| ${SHADER_HEADER} | |
| ../../include/ggml-webgpu.h | |
| ) | |
| add_dependencies(ggml-webgpu generate_shaders) | |
| if(EMSCRIPTEN) | |
| set(EMDAWNWEBGPU_DIR "" CACHE PATH "Path to emdawnwebgpu_pkg") | |
| if(NOT EMDAWNWEBGPU_DIR) | |
| # default built-in port | |
| target_compile_options(ggml-webgpu PRIVATE "--use-port=emdawnwebgpu") | |
| target_link_options(ggml-webgpu INTERFACE "--use-port=emdawnwebgpu") | |
| else() | |
| # custom port | |
| target_compile_options(ggml-webgpu PRIVATE "--use-port=${EMDAWNWEBGPU_DIR}/emdawnwebgpu.port.py") | |
| target_link_options(ggml-webgpu INTERFACE "--use-port=${EMDAWNWEBGPU_DIR}/emdawnwebgpu.port.py") | |
| endif() | |
| if (GGML_WEBGPU_JSPI) | |
| target_compile_options(ggml-webgpu PRIVATE "-fwasm-exceptions") | |
| target_link_options(ggml-webgpu INTERFACE "-sJSPI" "-fwasm-exceptions") | |
| else() | |
| target_compile_options(ggml-webgpu PRIVATE "-fexceptions") | |
| target_link_options(ggml-webgpu INTERFACE "-sASYNCIFY" "-exceptions") | |
| endif() | |
| else() | |
| find_package(Dawn REQUIRED) | |
| set(DawnWebGPU_TARGET dawn::webgpu_dawn) | |
| endif() | |
| if (GGML_WEBGPU_DEBUG) | |
| target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_DEBUG=1) | |
| if(EMSCRIPTEN) | |
| target_link_options(ggml-webgpu INTERFACE "-sASSERTIONS=2") | |
| endif() | |
| endif() | |
| if (GGML_WEBGPU_CPU_PROFILE) | |
| target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_CPU_PROFILE=1) | |
| endif() | |
| if (GGML_WEBGPU_GPU_PROFILE) | |
| target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_GPU_PROFILE=1) | |
| endif() | |
| target_include_directories(ggml-webgpu PRIVATE ${SHADER_OUTPUT_DIR}) | |
| target_link_libraries(ggml-webgpu PRIVATE ${DawnWebGPU_TARGET}) | |