Instructions to use tda45/TdAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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

TdAI / llama.cpp /ggml /src /ggml-opencl /kernels /concat.cl

tda45

Upload folder using huggingface_hub (part 4)

20a07ae verified 11 days ago

Raw

History Blame Contribute Delete

3.46 kB

	kernel void kernel_concat_f32(
	global const char * src0,
	ulong offset0,
	global const char * src1,
	ulong offset1,
	global char * dst,
	ulong offsetd,
	int ne00,
	int ne01,
	int ne02,
	int ne03,
	ulong nb00,
	ulong nb01,
	ulong nb02,
	ulong nb03,
	ulong nb10,
	ulong nb11,
	ulong nb12,
	ulong nb13,
	int ne0,
	ulong nb0,
	ulong nb1,
	ulong nb2,
	ulong nb3,
	int dim
	) {
	src0 = src0 + offset0;
	src1 = src1 + offset1;
	dst = dst + offsetd;

	const int i3 = get_group_id(2);
	const int i2 = get_group_id(1);
	const int i1 = get_group_id(0);

	int o[4] = {0, 0, 0, 0};
	o[dim] = dim == 0 ? ne00 : (dim == 1 ? ne01 : (dim == 2 ? ne02 : ne03));

	global const float * x;

	for (int i0 = get_local_id(0); i0 < ne0; i0 += get_local_size(0)) {
	if (i0 < ne00 && i1 < ne01 && i2 < ne02 && i3 < ne03) {
	x = (global const float )(src0 + (i3 )nb03 + (i2 )nb02 + (i1 )nb01 + (i0 )*nb00);
	} else {
	x = (global const float )(src1 + (i3 - o[3])nb13 + (i2 - o[2])nb12 + (i1 - o[1])nb11 + (i0 - o[0])*nb10);
	}

	global float * y = (global float )(dst + i3nb3 + i2nb2 + i1nb1 + i0*nb0);

	y = x;
	}
	}

	kernel void kernel_concat_f32_pack(
	global const char * src0,
	ulong offset0,
	global const char * src1,
	ulong offset1,
	global char * dst,
	ulong offsetd,
	int ne00,
	int ne01,
	int ne02,
	int ne03,
	ulong nb00,
	ulong nb01,
	ulong nb02,
	ulong nb03,
	ulong nb10,
	ulong nb11,
	ulong nb12,
	ulong nb13,
	int ne0,
	ulong nb0,
	ulong nb1,
	ulong nb2,
	ulong nb3,
	int dim,
	int ne1,
	int ne2,
	int ne3
	) {
	src0 = src0 + offset0;
	src1 = src1 + offset1;
	dst = dst + offsetd;

	int lsz = get_local_size(0);
	int tpr = min(ne0, lsz); // threads per row
	int rpw = lsz / tpr; // rows per workgroup
	int lid = get_local_id(0);
	int row = get_group_id(0)*rpw + lid / tpr;
	int lane = lid - (lid / tpr) * tpr;

	int nrows = ne1ne2ne3;
	if (row >= nrows) {
	return;
	}

	int i1 = row % ne1;
	int t = row / ne1;
	int i2 = t % ne2;
	int i3 = t / ne2;

	int o[4] = {0, 0, 0, 0};
	o[dim] = dim == 0 ? ne00 : (dim == 1 ? ne01 : (dim == 2 ? ne02 : ne03));

	for (int i0 = lane; i0 < ne0; i0 += tpr) {
	global const float * x;
	if (i0 < ne00 && i1 < ne01 && i2 < ne02 && i3 < ne03) {
	x = (global const float )(src0 + (i3 )nb03 + (i2 )nb02 + (i1 )nb01 + (i0 )*nb00);
	} else {
	x = (global const float )(src1 + (i3 - o[3])nb13 + (i2 - o[2])nb12 + (i1 - o[1])nb11 + (i0 - o[0])*nb10);
	}

	global float * y = (global float )(dst + i3nb3 + i2nb2 + i1nb1 + i0*nb0);

	y = x;
	}
	}