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
| int main(void) { | |
| printf("\n\nTesting libmtmd C API...\n"); | |
| printf("--------\n\n"); | |
| struct mtmd_context_params params = mtmd_context_params_default(); | |
| printf("Default image marker: %s\n", params.image_marker); | |
| mtmd_input_chunks * chunks = mtmd_test_create_input_chunks(); | |
| if (!chunks) { | |
| fprintf(stderr, "Failed to create input chunks\n"); | |
| return 1; | |
| } | |
| // simple test for the helper | |
| size_t n_tokens_total = mtmd_helper_get_n_tokens(chunks); | |
| printf("Total tokens in chunks: %zu\n", n_tokens_total); | |
| assert(n_tokens_total > 0); | |
| size_t n_chunks = mtmd_input_chunks_size(chunks); | |
| printf("Number of chunks: %zu\n", n_chunks); | |
| assert(n_chunks > 0); | |
| for (size_t i = 0; i < n_chunks; i++) { | |
| const mtmd_input_chunk * chunk = mtmd_input_chunks_get(chunks, i); | |
| assert(chunk != NULL); | |
| enum mtmd_input_chunk_type type = mtmd_input_chunk_get_type(chunk); | |
| printf("Chunk %zu type: %d\n", i, type); | |
| if (type == MTMD_INPUT_CHUNK_TYPE_TEXT) { | |
| size_t n_tokens; | |
| const llama_token * tokens = mtmd_input_chunk_get_tokens_text(chunk, &n_tokens); | |
| printf(" Text chunk with %zu tokens\n", n_tokens); | |
| assert(tokens != NULL); | |
| assert(n_tokens > 0); | |
| for (size_t j = 0; j < n_tokens; j++) { | |
| assert(tokens[j] >= 0); | |
| printf(" > Token %zu: %d\n", j, tokens[j]); | |
| } | |
| } else if (type == MTMD_INPUT_CHUNK_TYPE_IMAGE) { | |
| const mtmd_image_tokens * image_tokens = mtmd_input_chunk_get_tokens_image(chunk); | |
| size_t n_tokens = mtmd_image_tokens_get_n_tokens(image_tokens); | |
| // get position of the last token, which should be (nx - 1, ny - 1) | |
| struct mtmd_decoder_pos pos = mtmd_image_tokens_get_decoder_pos(image_tokens, 0, n_tokens - 1); | |
| size_t nx = pos.x + 1; | |
| size_t ny = pos.y + 1; | |
| const char * id = mtmd_image_tokens_get_id(image_tokens); | |
| assert(n_tokens > 0); | |
| assert(nx > 0); | |
| assert(ny > 0); | |
| assert(id != NULL); | |
| printf(" Image chunk with %zu tokens\n", n_tokens); | |
| printf(" Image size: %zu x %zu\n", nx, ny); | |
| printf(" Image ID: %s\n", id); | |
| } | |
| } | |
| // Free the chunks | |
| mtmd_input_chunks_free(chunks); | |
| printf("\n\nDONE: test libmtmd C API...\n"); | |
| return 0; | |
| } | |