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
| static inline void hex_dump_int8_line(char * pref, const int8_t * x, int n) { | |
| char str[1024], *p = str, *p_end = str + sizeof(str); | |
| p += snprintf(p, p_end - p, "%s: ", pref); | |
| for (int i = 0; i < n && p < p_end; i++) { | |
| p += snprintf(p, p_end - p, "%d, ", x[i]); | |
| } | |
| FARF(HIGH, "%s\n", str); | |
| } | |
| static inline void hex_dump_uint8_line(char * pref, const uint8_t * x, uint32_t n) { | |
| char str[1024], *p = str, *p_end = str + sizeof(str); | |
| p += snprintf(p, p_end - p, "%s: ", pref); | |
| for (int i = 0; i < n && p < p_end; i++) { | |
| p += snprintf(p, p_end - p, "%d, ", x[i]); | |
| } | |
| FARF(HIGH, "%s\n", str); | |
| } | |
| static inline void hex_dump_uint32_line(char * pref, const uint32_t * x, uint32_t n) { | |
| char str[1024], *p = str, *p_end = str + sizeof(str); | |
| p += snprintf(p, p_end - p, "%s: ", pref); | |
| for (int i = 0; i < n; i++) { | |
| p += snprintf(p, p_end - p, "%u, ", (unsigned int) x[i]); | |
| } | |
| FARF(HIGH, "%s\n", str); | |
| } | |
| static inline void hex_dump_int32_line(char * pref, const int32_t * x, uint32_t n) { | |
| char str[1024], *p = str, *p_end = str + sizeof(str); | |
| p += snprintf(p, p_end - p, "%s: ", pref); | |
| for (int i = 0; i < n; i++) { | |
| p += snprintf(p, p_end - p, "%d, ", (int) x[i]); | |
| } | |
| FARF(HIGH, "%s\n", str); | |
| } | |
| static inline void hex_dump_f16_line(char * pref, const __fp16 * x, uint32_t n) { | |
| char str[1024], *p = str, *p_end = str + sizeof(str); | |
| p += snprintf(p, p_end - p, "%s: ", pref); | |
| for (int i = 0; i < n; i++) { | |
| p += snprintf(p, p_end - p, "%.6f, ", (float) x[i]); | |
| } | |
| FARF(HIGH, "%s\n", str); | |
| } | |
| static inline void hex_dump_f32_line(char * pref, const float * x, uint32_t n) { | |
| char str[1024], *p = str, *p_end = str + sizeof(str); | |
| p += snprintf(p, p_end - p, "%s: ", pref); | |
| for (int i = 0; i < n; i++) { | |
| p += snprintf(p, p_end - p, "%.6f, ", x[i]); | |
| } | |
| FARF(HIGH, "%s\n", str); | |
| } | |
| static inline void hex_dump_f32(char * pref, const float * x, uint32_t n) { | |
| uint32_t n0 = n / 16; | |
| uint32_t n1 = n % 16; | |
| uint32_t i = 0; | |
| for (; i < n0; i++) { | |
| hex_dump_f32_line(pref, x + (16 * i), 16); | |
| } | |
| if (n1) { | |
| hex_dump_f32_line(pref, x + (16 * i), n1); | |
| } | |
| } | |
| static inline void hex_dump_f16(char * pref, const __fp16 * x, uint32_t n) { | |
| uint32_t n0 = n / 16; | |
| uint32_t n1 = n % 16; | |
| uint32_t i = 0; | |
| for (; i < n0; i++) { | |
| hex_dump_f16_line(pref, x + (16 * i), 16); | |
| } | |
| if (n1) { | |
| hex_dump_f16_line(pref, x + (16 * i), n1); | |
| } | |
| } | |