Text Generation
Safetensors
Rust
RWKV
English
oicio-rs
ternary
matmul-free
cpu-only
1.58-bit
bitnet
bonsai
infinite-context
em-llm
reattention
recursive-agent-harness
rlm
rah
edge-ai
needle
hadamard
mlgru
mamba
liquid-neural-networks
turbovec
turboquant
t-mac
vec-lut
axon
consumer-hardware
better-quality
intelligence-density
| { | |
| "model": "6.8M ternary", | |
| "vocab_size": 1024, | |
| "dim": 256, | |
| "layers": 4, | |
| "steps": 50, | |
| "batch_size": 4, | |
| "seq_len": 256, | |
| "initial_loss": 6.948805332183838, | |
| "final_loss": 6.937704563140869, | |
| "loss_drop": 0.01110076904296875, | |
| "time_seconds": 23.393130779266357, | |
| "fp16_mb": 13.008331298828125, | |
| "ternary_mb": 1.2845727157592775, | |
| "compression": 10.1, | |
| "swap": "14GB (10+5) active", | |
| "ram": "1.9GB", | |
| "hardware": "Consumer hardware only, no data center", | |
| "method_correct": true, | |
| "credits": "deepRcurs Labs @deeprcurs / Mzed Imamkh @mzedimamkh" | |
| } |