---

license: apache-2.0

base_model: h2oai/h2ovl-mississippi-800m

tags: [gguf, crispembed, ocr, vlm]

---

h2ovl-mississippi-800m — CrispEmbed GGUF

Edge-sized H2OVL for CrispEmbed.

Needs MSAC two-scale tiling and the h2ogpt2 prompt template (no BOS); the

runtime handles both.

| file | size | use |

|---|--:|---|

| h2ovl-800m-q4_k.gguf | 676 MB | default — edge/WASM, transcribes |

| h2ovl-800m-q8_0.gguf | 1175 MB | quality tier, vision tower at F16 |

Both transcribe a full scanned page (q4_k 1749 chars, q8_0 1764). The registry

ships q4_k deliberately: this is the small model, and the extra 499 MB does not

change the decoded output.

Parity

Per-stage against a Python-blueprint reference

(internvl2/h2ovl-mississippi-800m/ref.gguf in

cstr/crispembed-regression-fixtures),

CPU backend:

| stage | f16 | q8_0 |

|---|--:|--:|

| vis_proj_output | 0.999701 | 0.999701 |

| vis_pixel_unshuffle | 0.998199 | 0.998199 |

| llm_layer_0 | 1.000000 | 0.995712 |

| llm_layer_2 | 1.000000 | 0.494781 |

| decoded page | transcribes | transcribes |

The f16 LLM is exact. Read the q8_0 llm_layer_2 figure with care: 0.494781

looks alarming and the model still transcribes the page correctly. The probe is

a 5-token synthetic sequence, and on this checkpoint it does not track decoded

quality — the value that matters is the sign. A comparable-magnitude but

negative cosine (h2ovl-2b at q4_k, −0.27) does mean the output is wrong. The

decoded roundtrip is the acceptance gate here, not the cosine.

Attribution

Upstream © H2O.ai, Apache-2.0 — see

h2oai/h2ovl-mississippi-800m;

vision tower InternViT-300M is MIT. Conversion and quantization do not

relicense it. Per CrispEmbed POLICY.md, OCR output is a probabilistic

reconstruction, not a faithful copy.