Downloads · 30 days
49
15% of all-time downloads
h2ovl-800m-crispembed-GGUF
cstr/h2ovl-800m-crispembed-GGUF
h2ovl-800m-crispembed-GGUF is a machine learning model from cstr. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Edge-sized H2OVL for CrispEmbed. Needs MSAC two-scale tiling and the h2ogpt2 prompt template (no BOS); the runtime handles both.
All-time downloads
327
Public
Repo size
1.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf1.9 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 2, 2026
- Updated
- Aug 3, 2026
- SHA
- 7675e98d
Base models
Model card
From the Hugging Face model README
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.
- License
- apache-2.0
- Created
- Aug 2, 2026
- Updated
- Aug 3, 2026