ThoxMicro-1bit-9M
Your AI. Your Data. Your Rules.
From-scratch BitNet b1.58 ternary Llama (9M) trained on TinyStories — a story-completion / edge research artifact, not an assistant.
What this is
- Trained from scratch — no upstream base model.
- 76.4% of weights are ternary {-1,0,+1} (BitNet b1.58).
- License is unresolved: TinyStories (CDLA-Sharing-1.0) share-alike not yet cleared — treat as pending review, not open for redistribution until THOX confirms.
- Sibling: ThoxMicro-1bit-16M (deeper, not a replacement).
Architecture (from config)
| Field | Value |
|---|---|
| Architecture | BitNet b1.58 ternary Llama decoder |
| Layers | 8 |
| Hidden size | 256 |
| Attention heads | 8 |
| KV heads | 8 |
| FFN / intermediate | 768 |
| Vocab | 8,192 (own byte-level BPE) |
| Max context | 512 |
| Tied embeddings | yes |
Intended use
On-device / edge text generation within the THOX stack. Not a safety-aligned public assistant unless deployed behind THOX guardrails.
Usage
llama.cpp
huggingface-cli download Thox-ai/ThoxMicro-1bit-9M --include '*.gguf' --local-dir ./ThoxMicro-1bit-9M
llama-cli -m ./ThoxMicro-1bit-9M/model-TQ2_0.gguf -p "Hello"
Links
- Ollama:
ollama.com/thox-ai/<slug>— verify with the Ollama lane (task 80017303) - Docs: https://docs.thox.ai
THOX.ai LLC — Your AI. Your Data. Your Rules. · On-device and private by design.