Instructions to use Thox-ai/ThoxMicro-1bit-9M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Thox-ai/ThoxMicro-1bit-9M 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 Thox-ai/ThoxMicro-1bit-9M:Q8_0
# Run inference directly in the terminal:
llama cli -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0
# Run inference directly in the terminal:
llama cli -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0

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 Thox-ai/ThoxMicro-1bit-9M:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0

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 Thox-ai/ThoxMicro-1bit-9M:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0

Use Docker

docker model run hf.co/Thox-ai/ThoxMicro-1bit-9M:Q8_0

LM Studio
Jan

vLLM

How to use Thox-ai/ThoxMicro-1bit-9M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Thox-ai/ThoxMicro-1bit-9M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Thox-ai/ThoxMicro-1bit-9M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Thox-ai/ThoxMicro-1bit-9M:Q8_0

Ollama
How to use Thox-ai/ThoxMicro-1bit-9M with Ollama:
```
ollama run hf.co/Thox-ai/ThoxMicro-1bit-9M:Q8_0
```

Unsloth Studio

How to use Thox-ai/ThoxMicro-1bit-9M 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 Thox-ai/ThoxMicro-1bit-9M 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 Thox-ai/ThoxMicro-1bit-9M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Thox-ai/ThoxMicro-1bit-9M to start chatting

Docker Model Runner
How to use Thox-ai/ThoxMicro-1bit-9M with Docker Model Runner:
```
docker model run hf.co/Thox-ai/ThoxMicro-1bit-9M:Q8_0
```

Lemonade

How to use Thox-ai/ThoxMicro-1bit-9M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Thox-ai/ThoxMicro-1bit-9M:Q8_0

Run and chat with the model

lemonade run user.ThoxMicro-1bit-9M-Q8_0

List all available models

lemonade list

Atomic Chat

ThoxMicro-1bit-9M / Modelfile

tommytracx

Upload Modelfile with huggingface_hub

4aa5e0b verified 4 days ago

Raw

History Blame Contribute Delete

1.33 kB

	# ThoxMicro-1bit-9M — BitNet b1.58 ternary LLM, 8,917,248 params, trained from scratch on TinyStories.
	# This is a COMPLETION model. It has no chat template and no instruction tuning.
	# Do not add a SYSTEM prompt or a chat-style TEMPLATE — it cannot follow instructions.

	FROM ./thoxmicro-1bit-9m.TQ2_0.gguf

	# Bare prompt passthrough only. This model is not instruction-tuned, so the
	# template must not fake a chat turn or add an assistant role.
	TEMPLATE """{{ .Prompt }}"""

	# Tiny models degenerate into repetition without a repeat penalty; this is the
	# main guard against the model looping on a phrase.
	PARAMETER repeat_penalty 1.3

	# Stop token. Our own 8k BPE declares <pad>/<bos>/<eos>/<unk> -- NOT the
	# GPT-style <\|endoftext\|>, which appears nowhere in this vocabulary and would
	# therefore never fire. Verified against artifacts/ternary/tokenizer-8k.json.
	PARAMETER stop "<eos>"

	# Modest temperature: low enough to stay coherent, high enough to avoid
	# collapsing into the most common token on every step.
	PARAMETER temperature 0.8

	# Slight top_p truncation trims the long tail of unlikely tokens that a tiny
	# model tends to over-weight.
	PARAMETER top_p 0.9

	# License is UNSETTLED — trained on TinyStories (CDLA-Sharing-1.0). Pending
	# confirmation before a LICENSE line is added.