Views
No views yet
| Architecture | BitNet (BitNetForCausalLM) |
| Parameters | ~2B |
| Hidden size | 2560 |
| Layers | 30 |
| Attention heads | 20 (5 KV heads) |
| Context length | 4096 |
| Quantization | Ternary ({-1, 0, 1}) |
| Source model | microsoft/bitnet-b1.58-2B-4T-bf16 |
| License | MIT |
1pip install trillim
2trillim pull Trillim/BitNet-TRNQ
3trillim serve Trillim/BitNet-TRNQhttp://127.0.0.1:8000.trillim chat Trillim/BitNet-TRNQ| File | Description |
|---|---|
qmodel.tensors | Ternary-quantized weights in Trillim format |
rope.cache | Precomputed RoPE embeddings |
config.json | Model configuration |
tokenizer.json | Tokenizer |
tokenizer_config.json | Tokenizer configuration |
trillim_config.json | Trillim metadata |