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.
- 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
- 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
- Atomic Chat
| enable f16; | |
| @group(0) @binding(0) | |
| var<storage, read_write> src: array<SRC_TYPE>; | |
| @group(0) @binding(1) | |
| var<storage, read_write> dst: array<DST_TYPE>; | |
| struct Params{ | |
| ne: u32, | |
| offset_src: u32, | |
| offset_dst: u32, | |
| stride_src0: u32, | |
| stride_src1: u32, | |
| stride_src2: u32, | |
| stride_src3: u32, | |
| stride_dst0: u32, | |
| stride_dst1: u32, | |
| stride_dst2: u32, | |
| stride_dst3: u32, | |
| src_ne0: u32, | |
| src_ne1: u32, | |
| src_ne2: u32, | |
| dst_ne0: u32, | |
| dst_ne1: u32, | |
| dst_ne2: u32 | |
| }; | |
| @group(0) @binding(2) | |
| var<uniform> params: Params; | |
| @compute @workgroup_size(WG_SIZE) | |
| fn main( | |
| @builtin(global_invocation_id) gid: vec3<u32>, | |
| ) { | |
| if (gid.x >= params.ne) { | |
| return; | |
| } | |
| var i = gid.x; | |
| let i3 = i / (params.src_ne2 * params.src_ne1 * params.src_ne0); | |
| i = i % (params.src_ne2 * params.src_ne1 * params.src_ne0); | |
| let i2 = i / (params.src_ne1 * params.src_ne0); | |
| i = i % (params.src_ne1 * params.src_ne0); | |
| let i1 = i / params.src_ne0; | |
| let i0 = i % params.src_ne0; | |
| var j = gid.x; | |
| let j3 = j / (params.dst_ne2 * params.dst_ne1 * params.dst_ne0); | |
| j = j % (params.dst_ne2 * params.dst_ne1 * params.dst_ne0); | |
| let j2 = j / (params.dst_ne1 * params.dst_ne0); | |
| j = j % (params.dst_ne1 * params.dst_ne0); | |
| let j1 = j / params.dst_ne0; | |
| let j0 = j % params.dst_ne0; | |
| let src_idx = i0 * params.stride_src0 + i1 * params.stride_src1 + | |
| i2 * params.stride_src2 + i3 * params.stride_src3; | |
| let dst_idx = j0 * params.stride_dst0 + j1 * params.stride_dst1 + | |
| j2 * params.stride_dst2 + j3 * params.stride_dst3; | |
| dst[params.offset_dst + dst_idx] = DST_TYPE((src[params.offset_src + src_idx])); | |
| } | |