v0.5 — W8A8 FP8 (compressed-tensors, calibrated on 480 real pages), v0.5: v0.4.1 plus two supervised fine-tuning stages and a one-direction repetition-loop edit (1,024 MLP output columns, 0.066 % of weights); OmniDocBench v1.6 overall 77.12 to 83.45; requires shrew-server >= 0.5.0
13508bc verified Download tokenizer.json from btbtyler09/shrew-ocr-preview-FP8: direct link, hf CLI and curl.
- Browser
- Download file 7.15 MB
-
https://huggingface.co/btbtyler09/shrew-ocr-preview-FP8/resolve/main/tokenizer.json
- Command line
-
hf download hf://btbtyler09/shrew-ocr-preview-FP8/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/btbtyler09/shrew-ocr-preview-FP8/resolve/main/tokenizer.json
7.15 MB
File too large to display, you can check the raw version instead.