README.md

---
license: other
license_name: lfm1.0
license_link: LICENSE
base_model: LiquidAI/LFM2.5-Encoder-350M-Policy-Linter
pipeline_tag: token-classification
library_name: litert
tags:
- litert
- tflite
- on-device
- edge
- encoder
- zero-shot
- policy
- compliance
- liquid
- lfm2
- lfm2.5
---

# LFM2.5-Encoder-350M-Policy-Linter — LiteRT

[LiquidAI/LFM2.5-Encoder-350M-Policy-Linter](https://huggingface.co/LiquidAI/LFM2.5-Encoder-350M-Policy-Linter) converted to **LiteRT** (`.tflite`) for on-device inference. Zero-shot policy linting: write your rules as free text and the model scores **every token against every rule** in one CPU pass ([demo Space](https://huggingface.co/spaces/LiquidAI/policy-linting)).

| File | Recipe | Size | |
|---|---|---|---|
| `LFM2.5-Encoder-350M-Policy-Linter_wi8fc.tflite` | int8 dynamic-range (linears + embedding, convs float) | 365 MB | mobile + desktop (iPhone-verified bit-exact, 143 ms) |
| `LFM2.5-Encoder-350M-Policy-Linter_fp16.tflite` | fp16 weights, float compute | 713 MB | desktop — phone memory limits (XNNPACK per-signature fp32 unpacking) |

## Signatures

`lint_128` / `lint_512` (S = 128 / 512, batch 1, right-padded, up to **8 rule slots**):

| Input | Shape | |
|---|---|---|
| `input_ids` | int32 `[1, S]` | prompt tokens: `Policy:\n- <rule 1>\n- <rule 2>…\n\nText:\n<doc>` |
| `attention_mask` | int32 `[1, S]` | 1 = token, 0 = pad |
| `rule_pool` | float32 `[1, 8, S]` | row r = mean-pool weights over rule r's tokens (`1/n` each); unused rows all-zero |

Output: `scores` float32 `[1, S, 8]`, zeroed at padded positions. `sigmoid(score[t, r]) > 0.5` flags token t under rule r; read flags only for real rules and for the document's token range. The `rule_pool` build mirrors the router sibling's snippet ([LFM2.5-Encoder-350M-Prompt-Router](https://huggingface.co/litert-community/LFM2.5-Encoder-350M-Prompt-Router)) with the `Policy:` header.

## Verification

Task-level parity vs the PyTorch reference (demo: an email-address share + a delivery-date promise against two rules): fp32, fp16 and int8 all flag the **identical 10-token spans for both rules**. On an iPhone 17 Pro the int8 file reproduces the desktop outputs **bit-exactly** (cosine 1.000000, max diff 0.0) at 143 ms per `lint_512` pass (6 threads, XNNPACK).

## License

LFM Open License v1.0 (see `LICENSE`, unchanged from the base model). Note the license's commercial-use threshold (Section 5). This repository redistributes converted **Derivative Works** of LiquidAI/LFM2.5-Encoder-350M-Policy-Linter with modification notices per Section 4; all credit for the model to [Liquid AI](https://www.liquid.ai/).