commit e83ffc58c96cce8f755575efe43fcbecde6a1021 Author: ModelHub XC Date: Thu May 14 09:10:42 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GutenOCR-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b832a8c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GutenOCR-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GutenOCR-3B.IQ4_XS.gguf b/GutenOCR-3B.IQ4_XS.gguf new file mode 100644 index 0000000..b289b6b --- /dev/null +++ b/GutenOCR-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ef6994252d67665491020b5a8e000404e9bc6b0efbdac295dbb96531f52ed7 +size 1753187392 diff --git a/GutenOCR-3B.Q2_K.gguf b/GutenOCR-3B.Q2_K.gguf new file mode 100644 index 0000000..af7eb01 --- /dev/null +++ b/GutenOCR-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77b9ce9854485ff0b3af423672633f0cd8b10de8b2cc9aa4c43a5c5091623cc3 +size 1274758208 diff --git a/GutenOCR-3B.Q3_K_L.gguf b/GutenOCR-3B.Q3_K_L.gguf new file mode 100644 index 0000000..dd4eb4c --- /dev/null +++ b/GutenOCR-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8948acc480347bb5a1542d54542fd3df6fe1a20f0931ee59edc7993f95695a40 +size 1707394112 diff --git a/GutenOCR-3B.Q3_K_M.gguf b/GutenOCR-3B.Q3_K_M.gguf new file mode 100644 index 0000000..3433a3f --- /dev/null +++ b/GutenOCR-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8296860c2a33cb548e124778f07f6f1e71b857331d8b179b44fe64e038cea696 +size 1590477888 diff --git a/GutenOCR-3B.Q3_K_S.gguf b/GutenOCR-3B.Q3_K_S.gguf new file mode 100644 index 0000000..ebe0191 --- /dev/null +++ b/GutenOCR-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf074d0ffe4c541b6689d1ca788827b351974b4690290d64d0b119a43088188 +size 1454359616 diff --git a/GutenOCR-3B.Q4_K_M.gguf b/GutenOCR-3B.Q4_K_M.gguf new file mode 100644 index 0000000..de00183 --- /dev/null +++ b/GutenOCR-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bbceb4a8773205543771ae03dd1ba7bf42e6dff3f0c42162ec42a7ecc90a87e +size 1929905216 diff --git a/GutenOCR-3B.Q4_K_S.gguf b/GutenOCR-3B.Q4_K_S.gguf new file mode 100644 index 0000000..0b1fff7 --- /dev/null +++ b/GutenOCR-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59cc339ecaf3708119c67018c881ebb014237ee4b966cf29db4d5dbb36b0a41b +size 1834386496 diff --git a/GutenOCR-3B.Q5_K_M.gguf b/GutenOCR-3B.Q5_K_M.gguf new file mode 100644 index 0000000..60a6923 --- /dev/null +++ b/GutenOCR-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5916b53cfdc6c64872ecfa37cde30dceebc9dc37d8c1d45dfb26538204d3f280 +size 2224817216 diff --git a/GutenOCR-3B.Q5_K_S.gguf b/GutenOCR-3B.Q5_K_S.gguf new file mode 100644 index 0000000..30f3c65 --- /dev/null +++ b/GutenOCR-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfbb3151f533941083cdba240d26c8007a02ad82cc84a7490475058d34225a1b +size 2169668672 diff --git a/GutenOCR-3B.Q6_K.gguf b/GutenOCR-3B.Q6_K.gguf new file mode 100644 index 0000000..750b3b6 --- /dev/null +++ b/GutenOCR-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44ccd4f37e6ca6f729386d795b430836f6d540b698188c7ddda2e174937a23d8 +size 2538161216 diff --git a/GutenOCR-3B.Q8_0.gguf b/GutenOCR-3B.Q8_0.gguf new file mode 100644 index 0000000..b5f6b57 --- /dev/null +++ b/GutenOCR-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60edd404da73bef39299fbe88ee4c52a4fc6aecef33c42c66feea2c285a782ef +size 3285478464 diff --git a/GutenOCR-3B.f16.gguf b/GutenOCR-3B.f16.gguf new file mode 100644 index 0000000..00040ab --- /dev/null +++ b/GutenOCR-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f0192308666856bcb16a814d60a8aa8cc3736aad545d38e28cc065128b8afd1 +size 6178319424 diff --git a/GutenOCR-3B.mmproj-Q8_0.gguf b/GutenOCR-3B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..6e60bd4 --- /dev/null +++ b/GutenOCR-3B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a0330d055a176f086f3b1c7cadc7197ae103e0e14db21980c2a10fdee843708 +size 847768800 diff --git a/GutenOCR-3B.mmproj-f16.gguf b/GutenOCR-3B.mmproj-f16.gguf new file mode 100644 index 0000000..4489f39 --- /dev/null +++ b/GutenOCR-3B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31b5c8b02ae94bb7ee40f44d0ac8a801fcb8322a53f88f5a00e641c53e5f8f9b +size 1338428640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b527836 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +arxiv: 2601.1449 +base_model: rootsautomation/GutenOCR-3B +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- ocr +- vision +- qwen2.5-vl +- pdf +- document-understanding +--- +## About + + + + + + + + + +static quants of https://huggingface.co/rootsautomation/GutenOCR-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GutenOCR-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GutenOCR-3B-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GutenOCR-3B-GGUF/resolve/main/GutenOCR-3B.f16.gguf) | f16 | 6.3 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +