commit ebe1fdbb768c0ed029a0c07511288a2aab2f1e21 Author: ModelHub XC Date: Mon May 25 09:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/olmOCR-7B-thai-v3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..78aac47 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +olmOCR-7B-thai-v3.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.f16.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +olmOCR-7B-thai-v3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..098e215 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Adun/olmOCR-7B-thai-v3 +language: +- th +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Adun/olmOCR-7B-thai-v3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#olmOCR-7B-thai-v3-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-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/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.8 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/olmOCR-7B-thai-v3-GGUF/resolve/main/olmOCR-7B-thai-v3.f16.gguf) | f16 | 15.3 | 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. + + diff --git a/olmOCR-7B-thai-v3.IQ4_XS.gguf b/olmOCR-7B-thai-v3.IQ4_XS.gguf new file mode 100644 index 0000000..21cee88 --- /dev/null +++ b/olmOCR-7B-thai-v3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a9cd77af4b186f38d0d3d763cf16ac7334161d07de61ebeddea438e70445121 +size 4250297280 diff --git a/olmOCR-7B-thai-v3.Q2_K.gguf b/olmOCR-7B-thai-v3.Q2_K.gguf new file mode 100644 index 0000000..ab5d18a --- /dev/null +++ b/olmOCR-7B-thai-v3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb605df295ae9fdc561e4b93799b0e1c3d559d183212747e13d910f2a7fd0f29 +size 3015939008 diff --git a/olmOCR-7B-thai-v3.Q3_K_L.gguf b/olmOCR-7B-thai-v3.Q3_K_L.gguf new file mode 100644 index 0000000..c090d58 --- /dev/null +++ b/olmOCR-7B-thai-v3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f137c5b68c76ef6f010b825eb146e6af664b69a3aa3626c5e6b587e4af622d95 +size 4088458176 diff --git a/olmOCR-7B-thai-v3.Q3_K_M.gguf b/olmOCR-7B-thai-v3.Q3_K_M.gguf new file mode 100644 index 0000000..f47f730 --- /dev/null +++ b/olmOCR-7B-thai-v3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af7673c15fe2465d5664318d95d75b37ba3d3bb2943da121150bfcac09823bad +size 3808390080 diff --git a/olmOCR-7B-thai-v3.Q3_K_S.gguf b/olmOCR-7B-thai-v3.Q3_K_S.gguf new file mode 100644 index 0000000..79f8273 --- /dev/null +++ b/olmOCR-7B-thai-v3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d17fe6698be205bf32848798a43530f881d751adc48752f61e8003db076d443 +size 3492367296 diff --git a/olmOCR-7B-thai-v3.Q4_K_M.gguf b/olmOCR-7B-thai-v3.Q4_K_M.gguf new file mode 100644 index 0000000..8aabdae --- /dev/null +++ b/olmOCR-7B-thai-v3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3f9fb60338000e3bdd5ef5249447f74f67842f13e588acd1c73b8d02c7da25 +size 4683072448 diff --git a/olmOCR-7B-thai-v3.Q4_K_S.gguf b/olmOCR-7B-thai-v3.Q4_K_S.gguf new file mode 100644 index 0000000..a1b57f8 --- /dev/null +++ b/olmOCR-7B-thai-v3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b8076768258f070bc9691b9aa5a5de18c8cbfea9238382edc3c8501c38ed4c +size 4457767872 diff --git a/olmOCR-7B-thai-v3.Q5_K_M.gguf b/olmOCR-7B-thai-v3.Q5_K_M.gguf new file mode 100644 index 0000000..b49a206 --- /dev/null +++ b/olmOCR-7B-thai-v3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ac075878ede76c84047f3c66ad4498d4fa44e0ea04d99d182415af241ba1cd +size 5444830144 diff --git a/olmOCR-7B-thai-v3.Q5_K_S.gguf b/olmOCR-7B-thai-v3.Q5_K_S.gguf new file mode 100644 index 0000000..3aa3d06 --- /dev/null +++ b/olmOCR-7B-thai-v3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b094fe4f3293d7284372006cbc0fe781abf0baf672c28f33ee5a4c90749a88f2 +size 5315175360 diff --git a/olmOCR-7B-thai-v3.Q6_K.gguf b/olmOCR-7B-thai-v3.Q6_K.gguf new file mode 100644 index 0000000..eab0048 --- /dev/null +++ b/olmOCR-7B-thai-v3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30191330df38f0f6ef936056e24e1ce73facc198327e00609bdb2d98095a3018 +size 6254197696 diff --git a/olmOCR-7B-thai-v3.Q8_0.gguf b/olmOCR-7B-thai-v3.Q8_0.gguf new file mode 100644 index 0000000..5e089d0 --- /dev/null +++ b/olmOCR-7B-thai-v3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ec7321b088d1f49a8a4db7be424464e935853b9c1448b1cf53854975aa58ec +size 8098524096 diff --git a/olmOCR-7B-thai-v3.f16.gguf b/olmOCR-7B-thai-v3.f16.gguf new file mode 100644 index 0000000..9dda19c --- /dev/null +++ b/olmOCR-7B-thai-v3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32820c9f614904a1d793cbfd2254c9b15a8f5957b894851b59c726aacb231c78 +size 15237852096 diff --git a/olmOCR-7B-thai-v3.mmproj-Q8_0.gguf b/olmOCR-7B-thai-v3.mmproj-Q8_0.gguf new file mode 100644 index 0000000..0fffcd4 --- /dev/null +++ b/olmOCR-7B-thai-v3.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e89ce087165be20cd3e8d913c7723fb648e7449a292ea6f41bc065ce868c25fd +size 721032288 diff --git a/olmOCR-7B-thai-v3.mmproj-f16.gguf b/olmOCR-7B-thai-v3.mmproj-f16.gguf new file mode 100644 index 0000000..e7fd68b --- /dev/null +++ b/olmOCR-7B-thai-v3.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9dcbb5444f64128ec67b5ba61a1de042bf602d4d8ff05e6eca0b4dcfea83239 +size 1352635488