| --- |
| license: other |
| license_name: lfm-open-license-v1.0 |
| license_link: https://huggingface.co/LiquidAI/LFM2.5-Encoder-350M/blob/main/LICENSE |
| library_name: minima-lfm |
| base_model: LiquidAI/LFM2.5-Encoder-350M |
| tags: |
| - ternary |
| - 1.58-bit |
| - encoder |
| - cpu |
| --- |
| |
| # Minima |
|
|
| A W1.58A8 adaptation of |
| [LiquidAI/LFM2.5-Encoder-350M](https://huggingface.co/LiquidAI/LFM2.5-Encoder-350M), |
| built with [SSHDotCodes/minima](https://github.com/SSHDotCodes/minima). |
|
|
| - Logical matrix values: `{-1, 0, +1}` (1.585 bits) |
| - Physical artifact format: I2_S, four trits per byte |
| - Dynamic int8 activations |
| - Group size 32 with rank-128 FP16 recovery adapters |
| - Full 8,192-token encoder context |
| - 223.9 MB weight file, 84.2% smaller than the 1,418.0 MB source weight file |
| |
| ## Use |
| |
| ```bash |
| pip install "minima-lfm @ git+https://github.com/SSHDotCodes/minima.git" |
| ``` |
| |
| ```python |
| from minima import MinimaModel |
| |
| model = MinimaModel.from_pretrained("ProCreations/minima", device="cpu") |
| outputs = model(input_ids=input_ids, attention_mask=attention_mask) |
| ``` |
| |
| CPU inference defaults to a one-time FBGEMM dynamic-int8 packing of each |
| effective ternary-plus-recovery matrix, after which source projection tensors are |
| released. Set `MINIMA_CPU_BACKEND=i2s` for the direct packed 2-bit AVX2/ARM NEON |
| kernel. The direct I2_S path has the smaller projection representation; the |
| FBGEMM path is the measured throughput default. |
| |
| ## Measured CPU results |
| |
| Hugging Face `cpu-performance`, Linux x86-64, FBGEMM, 16 threads, one warmup and |
| five measured runs: |
| |
| | Sequence | FP32 median | Minima median | Speedup | Peak RSS reduction | |
| |---:|---:|---:|---:|---:| |
| | 128 | 181.62 ms | 80.82 ms | 2.25x | 23.81% | |
| | 512 | 479.12 ms | 247.94 ms | 1.93x | 26.77% | |
| | 2,048 | 1,402.74 ms | 1,280.92 ms | 1.10x | 26.94% | |
| | 8,192 | 7,878.43 ms | 7,312.03 ms | 1.08x | 24.42% | |
| |
| Peak RSS includes framework and activation memory, so it does not shrink by the |
| same 84.2% as the weight file. Raw reports are in the |
| [results dataset](https://huggingface.co/datasets/ProCreations/minima-results). |
| |
| ## Encoder quality |
| |
| The six-task downstream gate retained **96.66%** of the matched FP32 baseline |
| after per-task ratios were capped at 100%. Five non-CoLA tasks averaged 98.05%; |
| CoLA retained 89.70%. This misses the declared 97% threshold by 0.34 percentage |
| points, so this artifact is a **release candidate**, not a quality-gated release. |
| The validation-selected CoLA schedule and all eight candidates are published in |
| the [raw report](https://huggingface.co/datasets/ProCreations/minima-results/blob/main/quality_gate.json). |
| |
| ## CUDA status |
| |
| The fused Triton path avoids materializing a full dequantized weight tensor and |
| passes correctness checks, but the current kernel is slower than upstream BF16 |
| on an H200. It is included for optimization work, not advertised as a GPU speedup. |
| |
| ## Diagnostics |
| |
| The release distillation probe measured hidden-state cosine 0.8491, relative L2 |
| 0.5877, and 99.67% masked-token top-1 agreement across 601 positions. These are |
| diagnostics; the downstream task gate above is the release-quality measure. |
| |
| ## License |
| |
| The weights remain subject to the LFM Open License v1.0 shipped in this |
| repository. The Minima runtime code is MIT licensed. |
| |
