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
| include(CheckCSourceRuns) | |
| set(AVX_CODE " | |
| #include <immintrin.h> | |
| int main() | |
| { | |
| __m256 a; | |
| a = _mm256_set1_ps(0); | |
| return 0; | |
| } | |
| ") | |
| set(AVX512_CODE " | |
| #include <immintrin.h> | |
| int main() | |
| { | |
| __m512i a = _mm512_set_epi8(0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0, | |
| 0, 0, 0, 0, 0, 0, 0, 0); | |
| __m512i b = a; | |
| __mmask64 equality_mask = _mm512_cmp_epi8_mask(a, b, _MM_CMPINT_EQ); | |
| return 0; | |
| } | |
| ") | |
| set(AVX2_CODE " | |
| #include <immintrin.h> | |
| int main() | |
| { | |
| __m256i a = {0}; | |
| a = _mm256_abs_epi16(a); | |
| __m256i x; | |
| _mm256_extract_epi64(x, 0); // we rely on this in our AVX2 code | |
| return 0; | |
| } | |
| ") | |
| set(FMA_CODE " | |
| #include <immintrin.h> | |
| int main() | |
| { | |
| __m256 acc = _mm256_setzero_ps(); | |
| const __m256 d = _mm256_setzero_ps(); | |
| const __m256 p = _mm256_setzero_ps(); | |
| acc = _mm256_fmadd_ps( d, p, acc ); | |
| return 0; | |
| } | |
| ") | |
| macro(check_sse type flags) | |
| set(__FLAG_I 1) | |
| set(CMAKE_REQUIRED_FLAGS_SAVE ${CMAKE_REQUIRED_FLAGS}) | |
| foreach (__FLAG ${flags}) | |
| if (NOT ${type}_FOUND) | |
| set(CMAKE_REQUIRED_FLAGS ${__FLAG}) | |
| check_c_source_runs("${${type}_CODE}" HAS_${type}_${__FLAG_I}) | |
| if (HAS_${type}_${__FLAG_I}) | |
| set(${type}_FOUND TRUE CACHE BOOL "${type} support") | |
| set(${type}_FLAGS "${__FLAG}" CACHE STRING "${type} flags") | |
| endif() | |
| math(EXPR __FLAG_I "${__FLAG_I}+1") | |
| endif() | |
| endforeach() | |
| set(CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS_SAVE}) | |
| if (NOT ${type}_FOUND) | |
| set(${type}_FOUND FALSE CACHE BOOL "${type} support") | |
| set(${type}_FLAGS "" CACHE STRING "${type} flags") | |
| endif() | |
| mark_as_advanced(${type}_FOUND ${type}_FLAGS) | |
| endmacro() | |
| # flags are for MSVC only! | |
| check_sse("AVX" " ;/arch:AVX") | |
| if (NOT ${AVX_FOUND}) | |
| set(GGML_AVX OFF) | |
| else() | |
| set(GGML_AVX ON) | |
| endif() | |
| check_sse("AVX2" " ;/arch:AVX2") | |
| check_sse("FMA" " ;/arch:AVX2") | |
| if ((NOT ${AVX2_FOUND}) OR (NOT ${FMA_FOUND})) | |
| set(GGML_AVX2 OFF) | |
| else() | |
| set(GGML_AVX2 ON) | |
| endif() | |
| check_sse("AVX512" " ;/arch:AVX512") | |
| if (NOT ${AVX512_FOUND}) | |
| set(GGML_AVX512 OFF) | |
| else() | |
| set(GGML_AVX512 ON) | |
| endif() | |