commit d12d25f0e54d7b029410ba5b359c63d636da5b57 Author: ModelHub XC Date: Thu Jul 16 11:23:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..361c4be --- /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 +Qwen2-VL-OCR2-2B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-VL-OCR2-2B-Instruct.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-VL-OCR2-2B-Instruct.IQ4_XS.gguf b/Qwen2-VL-OCR2-2B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..bb85ca4 --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01acd0c972ac3b7f0e219f37cb69ba1b824d3cd2a58c4fec6a8b3e363ffaddf3 +size 902182752 diff --git a/Qwen2-VL-OCR2-2B-Instruct.Q2_K.gguf b/Qwen2-VL-OCR2-2B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..6a47caf --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29411156a1f437f4da0de3562b19e50483032fb30b1d3b2ab1b6f144442af8f5 +size 676304736 diff --git a/Qwen2-VL-OCR2-2B-Instruct.Q3_K_L.gguf b/Qwen2-VL-OCR2-2B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..7b907fa --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfe050286e96201ae65d44f4d67790e4340e1b61fe094e1c23ce81f6b0a9a0fb +size 880162656 diff --git a/Qwen2-VL-OCR2-2B-Instruct.Q3_K_M.gguf b/Qwen2-VL-OCR2-2B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..ebb9294 --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd71c1192eda18bd9c02ba522d60c499e982f4edf88c2691919d12f2f6f605a5 +size 824178528 diff --git a/Qwen2-VL-OCR2-2B-Instruct.Q3_K_S.gguf b/Qwen2-VL-OCR2-2B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..7255ec3 --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceaa2627e58ff320b5590983ebdcd92eff5d46dfc2da3310c208e68de68dcc2e +size 760944480 diff --git a/Qwen2-VL-OCR2-2B-Instruct.Q4_K_M.gguf b/Qwen2-VL-OCR2-2B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..44c8757 --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1abbf8dcbbe59a1f3febea360a0723ab9152ddbc4aa7dfd717729f1ae6ad1773 +size 986048352 diff --git a/Qwen2-VL-OCR2-2B-Instruct.Q4_K_S.gguf b/Qwen2-VL-OCR2-2B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..b0e8509 --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:900485bb05544717d9a3768d5bced8a72c45e08f1fdd033ed37907c18e4785c4 +size 940312416 diff --git a/Qwen2-VL-OCR2-2B-Instruct.Q5_K_M.gguf b/Qwen2-VL-OCR2-2B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..e8876f8 --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5a50bb4edf1f65c522a549a6c141be7a510ad19052a60fdf29f505ca47e9e7 +size 1125050208 diff --git a/Qwen2-VL-OCR2-2B-Instruct.Q5_K_S.gguf b/Qwen2-VL-OCR2-2B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..08edb54 --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e99a4da5be2c1ef5418656cfcf32e456a55ebe391cf3f8e90617e0b1814d08b +size 1098729312 diff --git a/Qwen2-VL-OCR2-2B-Instruct.Q6_K.gguf b/Qwen2-VL-OCR2-2B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..75c1a74 --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0b740d80ae95dfc252f7a1ada57a2998950b7780b5a43310b6dff60ddbbe4ad +size 1272739680 diff --git a/Qwen2-VL-OCR2-2B-Instruct.Q8_0.gguf b/Qwen2-VL-OCR2-2B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..b88c4f5 --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d856070496c3f4c24fbfd6ec5cd8ae58f7e8aa1084f30a70ac8b189a28fe9a8c +size 1646572896 diff --git a/Qwen2-VL-OCR2-2B-Instruct.f16.gguf b/Qwen2-VL-OCR2-2B-Instruct.f16.gguf new file mode 100644 index 0000000..370cf91 --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d63a794fecdcede1206647f47b78fa5c1627882d17c6488f6cf9dc35aab0ca5 +size 3093669216 diff --git a/Qwen2-VL-OCR2-2B-Instruct.mmproj-fp16.gguf b/Qwen2-VL-OCR2-2B-Instruct.mmproj-fp16.gguf new file mode 100644 index 0000000..d14facb --- /dev/null +++ b/Qwen2-VL-OCR2-2B-Instruct.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5cf51de7471e0955ae3766957f03d9ba5c4881c26219cafd32d549f32cd30bc +size 1331656192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5395cce --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: prithivMLmods/Qwen2-VL-OCR2-2B-Instruct +datasets: +- linxy/LaTeX_OCR +- unsloth/LaTeX_OCR +- v1v1d/Latexify_v1 +- lamm-mit/OleehyO-latex-formulas +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- ocr +- vl +- qwen2_vl +- 2B +- VQA +- KIE +- Latex +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Qwen2-VL-OCR2-2B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2-VL-OCR2-2B-Instruct-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-VL-OCR2-2B-Instruct-GGUF/resolve/main/Qwen2-VL-OCR2-2B-Instruct.f16.gguf) | f16 | 3.2 | 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. + +