commit 2d24166b27f94dbd2e138ae4d72b5f169f68a541 Author: ModelHub XC Date: Thu Apr 23 09:22:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Bangla-OCR-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d70fb23 --- /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 +Bangla-OCR-SFT.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Bangla-OCR-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bangla-OCR-SFT.IQ4_XS.gguf b/Bangla-OCR-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..61051b9 --- /dev/null +++ b/Bangla-OCR-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a95f1cb0b51bb1e6d18bb169d5060bdd22951530a049e2dceb71771f5fffa04 +size 1016282400 diff --git a/Bangla-OCR-SFT.Q2_K.gguf b/Bangla-OCR-SFT.Q2_K.gguf new file mode 100644 index 0000000..e88f89c --- /dev/null +++ b/Bangla-OCR-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e8283fd088cad24778537d5173962754c29ba5461c56277d955297829b1a93 +size 777796896 diff --git a/Bangla-OCR-SFT.Q3_K_L.gguf b/Bangla-OCR-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..982ee22 --- /dev/null +++ b/Bangla-OCR-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9e8ca16a7eda4daa106ad9e27bba559247c4a0171e45bdbd1407a01026d5c8 +size 1003502880 diff --git a/Bangla-OCR-SFT.Q3_K_M.gguf b/Bangla-OCR-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..3d0c8b4 --- /dev/null +++ b/Bangla-OCR-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd56b4bcb2983ab12f286cfb07f40261feff85c4d9b5b1578a96fd74e84a1ac +size 939539744 diff --git a/Bangla-OCR-SFT.Q3_K_S.gguf b/Bangla-OCR-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..143d1b1 --- /dev/null +++ b/Bangla-OCR-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae5a6bf5e92ea9fb63e26b31181329853b8e8e633ad889d8dbe0c03e73f08c8 +size 867253536 diff --git a/Bangla-OCR-SFT.Q4_K_M.gguf b/Bangla-OCR-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..b545ba1 --- /dev/null +++ b/Bangla-OCR-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44bfe2c53a88ecbe0e4d87bf2872554278f70f6e91bff713e3f14e0802f425dc +size 1107410208 diff --git a/Bangla-OCR-SFT.Q4_K_S.gguf b/Bangla-OCR-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..9f6e3c1 --- /dev/null +++ b/Bangla-OCR-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7618d216b0a8e519567029d0bd8522bc6a19c4b987f4aaab8ee5c1697b775a +size 1060191520 diff --git a/Bangla-OCR-SFT.Q5_K_M.gguf b/Bangla-OCR-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..0431b4f --- /dev/null +++ b/Bangla-OCR-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e52464688a19b6877e5f90c77361f210958d077f688f6bc95ad7aa684f74c5d2 +size 1257880864 diff --git a/Bangla-OCR-SFT.Q5_K_S.gguf b/Bangla-OCR-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..9fc05ed --- /dev/null +++ b/Bangla-OCR-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76f116ab8d2afc255a9970dfe3a27855ac00c66835c0f7076c99e856ce68fe69 +size 1230585120 diff --git a/Bangla-OCR-SFT.Q6_K.gguf b/Bangla-OCR-SFT.Q6_K.gguf new file mode 100644 index 0000000..edd9196 --- /dev/null +++ b/Bangla-OCR-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0672971af8152ddc1da6586791d0f9610b99584cc6c63a68d87c6dbf63673f83 +size 1417755936 diff --git a/Bangla-OCR-SFT.Q8_0.gguf b/Bangla-OCR-SFT.Q8_0.gguf new file mode 100644 index 0000000..3e4341d --- /dev/null +++ b/Bangla-OCR-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20385ef723c6d00bb2d6b1bb152dec9ab4d765db803b412e57f691cf961c835b +size 1834427680 diff --git a/Bangla-OCR-SFT.f16.gguf b/Bangla-OCR-SFT.f16.gguf new file mode 100644 index 0000000..5d48444 --- /dev/null +++ b/Bangla-OCR-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5987c4490859639c5ce8e34466f5503aed2509a9534028bb9e9db621a8c78cbf +size 3447350560 diff --git a/Bangla-OCR-SFT.mmproj-Q8_0.gguf b/Bangla-OCR-SFT.mmproj-Q8_0.gguf new file mode 100644 index 0000000..5cd6f09 --- /dev/null +++ b/Bangla-OCR-SFT.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba6a8994fdf5732d3d87568087ec9ca6c8fc1892a3025aefbb591657603cad0 +size 445052992 diff --git a/Bangla-OCR-SFT.mmproj-f16.gguf b/Bangla-OCR-SFT.mmproj-f16.gguf new file mode 100644 index 0000000..3e76607 --- /dev/null +++ b/Bangla-OCR-SFT.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:796b2fec99f21333308e5fea815cff98cb4763f020ba16437e79c4a85a72a346 +size 819394624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..415589e --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: swapnillo/Bangla-OCR-SFT +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/swapnillo/Bangla-OCR-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Bangla-OCR-SFT-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/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Bangla-OCR-SFT-GGUF/resolve/main/Bangla-OCR-SFT.f16.gguf) | f16 | 3.5 | 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. + +