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
| /** Checks is a value is a power of two. Does not handle zero. */ | |
| /** Checks is a value is a power of two. Zero handled. */ | |
| /** Align a value to a power of two */ | |
| static inline bool util_is_power_of_two_nonzero64(uint64_t v) { | |
| return IS_POT_NONZERO(v); | |
| } | |
| static inline uint64_t align64(uint64_t value, uint64_t alignment) { | |
| assert(util_is_power_of_two_nonzero64(alignment)); | |
| return ALIGN_POT(value, alignment); | |
| } | |
| struct list_head { | |
| list_head * prev; | |
| list_head * next; | |
| }; | |
| struct util_sparse_array { | |
| size_t elem_size; | |
| unsigned node_size_log2; | |
| uintptr_t root; | |
| }; | |
| void * util_sparse_array_get(util_sparse_array * arr, uint64_t idx); | |
| void util_sparse_array_init(util_sparse_array * arr, size_t elem_size, size_t node_size); | |
| inline void os_time_sleep(int64_t usecs) { | |
| timespec time; | |
| time.tv_sec = usecs / 1000000; | |
| time.tv_nsec = (usecs % 1000000) * 1000; | |
| while (clock_nanosleep(CLOCK_MONOTONIC, 0, &time, &time) == EINTR) | |
| ; | |
| } | |
| struct timer_data { | |
| long long start; | |
| long long total; | |
| long long count; | |
| }; | |
| static inline void start_timer(timer_data * timer) { | |
| timespec ts; | |
| clock_gettime(CLOCK_MONOTONIC, &ts); | |
| timer->start = (long long) ts.tv_sec * 1000000000LL + ts.tv_nsec; | |
| } | |
| // returns the duration in ns | |
| static inline long long stop_timer(timer_data * timer) { | |
| timespec ts; | |
| clock_gettime(CLOCK_MONOTONIC, &ts); | |
| long long timer_end = (long long) ts.tv_sec * 1000000000LL + ts.tv_nsec; | |
| long long duration = (timer_end - timer->start); | |
| timer->total += duration; | |
| timer->count += 1; | |
| return duration; | |
| } | |