Downloads · 30 days
62
7% of all-time downloads
h2ovl-mississippi-2b-crispembed-GGUF
cstr/h2ovl-mississippi-2b-crispembed-GGUF
h2ovl-mississippi-2b-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.
H2OVL-Mississippi-2B for CrispEmbed. Needs MSAC two-scale tiling and the h2ogpt2 prompt template (no BOS) — all handled by the runtime.
All-time downloads
865
Public
Repo size
17.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf7.3 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 2, 2026
- Updated
- Aug 3, 2026
- SHA
- 1c620f2a
Base models
Model card
From the Hugging Face model README
h2ovl-mississippi-2b — CrispEmbed GGUF
H2OVL-Mississippi-2B for CrispEmbed.
Needs MSAC two-scale tiling and the h2ogpt2 prompt template (no BOS) — all
handled by the runtime.
crispembed -m h2ovl-mississippi-2b-q8_0.gguf --ocr page.png
| file | size | verdict |
|---|---|---|
h2ovl-mississippi-2b-f16.gguf | 4636 MB | reference precision |
h2ovl-mississippi-2b-q8_0.gguf | 2592 MB | recommended — vision tower held at F16 |
| — | withdrawn, measured broken |
Parity
Per-stage against a reference dumped from the Python blueprint
(internvl2/h2ovl-mississippi-2b/ref.gguf in
cstr/crispembed-regression-fixtures),
CPU backend, plus the decoded output on a full scanned page:
| stage | f16 | q8_0 (shipped) | q4_k |
|---|---|---|---|
| vis_proj_output | 0.999974 | 0.999974 | 0.912992 |
| vis_pixel_unshuffle | 0.999691 | 0.999691 | 0.380373 |
| llm_layer_0 | 1.000000 | 0.982747 | 0.594995 |
| llm_layer_3 | 1.000000 | 0.962142 | −0.279113 |
| decoded page | transcribes | transcribes | fluent but wrong |
The shipped q8_0 keeps the vision tower at F16 — that costs ~13 % size and lifts every vision stage to the f16 ceiling. The InternViT encoder is 24 residual blocks, so per-weight error compounds: at Q8_0 the tower drifts to 0.90 by layer 11, and the projector output falls to 0.913. The decoder stays Q8_0, where the output is correct.
q4_k was withdrawn. It loads and produces confident, well-formed text that
is not what is on the page — the worst failure mode for OCR. Its decoder is
anti-correlated with the reference by layer 2. Checkpoint-specific:
internvl2-1b and h2ovl-800m are fine at q4_k.
Attribution
Upstream © H2O.ai, Apache-2.0 — see
h2oai/h2ovl-mississippi-2b;
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