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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use navthings/lilchat 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 navthings/lilchat:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf navthings/lilchat:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf navthings/lilchat:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf navthings/lilchat:Q4_K_M

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 navthings/lilchat:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf navthings/lilchat:Q4_K_M

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 navthings/lilchat:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf navthings/lilchat:Q4_K_M

Use Docker

docker model run hf.co/navthings/lilchat:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use navthings/lilchat with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/navthings/lilchat:Q4_K_M

Ollama
How to use navthings/lilchat with Ollama:
```
ollama run hf.co/navthings/lilchat:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use navthings/lilchat with Docker Model Runner:
```
docker model run hf.co/navthings/lilchat:Q4_K_M
```

Lemonade

How to use navthings/lilchat with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull navthings/lilchat:Q4_K_M

Run and chat with the model

lemonade run user.lilchat-Q4_K_M

List all available models

lemonade list

Atomic Chat

lilchat

lilbase (297m params, trained from scratch) finetuned into a chat model on smol-smoltalk.

it follows the chat format, answers in full sentences, stops when its done, and does lists and code blocks. it does not know things. expect confident wrong answers on facts and maths, and weak memory across turns.

run it

ollama run navthings/lilchat

or try it in your browser: https://navthings.github.io/playground/

files

file	size	notes
`model.safetensors` + config + tokenizer	1.19gb	transformers `LlamaForCausalLM`, chat template included
`lilchat-q8_0.gguf`	379mb
`lilchat-q4_k_m.gguf`	274mb	smallest

prompt format

llama-2 style, with </s> (id 2) as the start token and after every assistant reply:

</s>[INST] hi [/INST] Hello! How can I help you today?</s>[INST] next message [/INST]

system prompts go in <<SYS>>\n...\n<</SYS>>\n\n before the first [INST].

finetune

full sft in mlx on a macbook air, 1,136 steps of 32k tokens (~37m tokens, about 12% of smol-smoltalk), loss only on assistant turns. held-out loss 1.337 vs 2.230 for lilbase on the same data.

temperature 0.4 works best. greedy decoding loops, keep some temperature.

code

https://github.com/navthings/sprout (sft/)

Downloads last month: 284

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for navthings/lilchat

Base model

navthings/lilbase

Quantized

(1)

this model

navthings
/

lilchat