Instructions to use Clem-CPu/Tiny-lamina-english-fragment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Clem-CPu/Tiny-lamina-english-fragment 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 Clem-CPu/Tiny-lamina-english-fragment
# Run inference directly in the terminal:
llama cli -hf Clem-CPu/Tiny-lamina-english-fragment

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Clem-CPu/Tiny-lamina-english-fragment
# Run inference directly in the terminal:
llama cli -hf Clem-CPu/Tiny-lamina-english-fragment

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 Clem-CPu/Tiny-lamina-english-fragment
# Run inference directly in the terminal:
./llama-cli -hf Clem-CPu/Tiny-lamina-english-fragment

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 Clem-CPu/Tiny-lamina-english-fragment
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Clem-CPu/Tiny-lamina-english-fragment

Use Docker

docker model run hf.co/Clem-CPu/Tiny-lamina-english-fragment

LM Studio
Jan

vLLM

How to use Clem-CPu/Tiny-lamina-english-fragment with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Clem-CPu/Tiny-lamina-english-fragment"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Clem-CPu/Tiny-lamina-english-fragment",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Clem-CPu/Tiny-lamina-english-fragment

Ollama
How to use Clem-CPu/Tiny-lamina-english-fragment with Ollama:
```
ollama run hf.co/Clem-CPu/Tiny-lamina-english-fragment
```
Unsloth Desktop
Docker Model Runner
How to use Clem-CPu/Tiny-lamina-english-fragment with Docker Model Runner:
```
docker model run hf.co/Clem-CPu/Tiny-lamina-english-fragment
```

Lemonade

How to use Clem-CPu/Tiny-lamina-english-fragment with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Clem-CPu/Tiny-lamina-english-fragment

Run and chat with the model

lemonade run user.Tiny-lamina-english-fragment-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

Tiny-lamina is an extremely lightweight language model, designed specifically for children and normal users on simple phone CPUs. with only 202k parameters, Tiny-lamina is extremely ultra-compact, allowing fine-tuning on CPUs and uses on low-end phones.

The use cases of this tiny-lamina aim to generate English word fragments for all use cases that require unstructured English words, or fragments of English prepositions.

Tiny-lamina, and all the models on the Clem-CPu account, aim to democratize the use of AI models by children on CPUs.

Downloads last month: 5

GGUF

Model size

202k params

Architecture

gpt2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants