commit e6d63afadcbf23319910ab8fbd14f1024218edf7 Author: ModelHub XC Date: Thu Apr 30 20:30:45 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9242abd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.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 +MasriSwitch-Gemma3n-Transcriber-v1.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_M.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_M.gguf new file mode 100644 index 0000000..3daaed7 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8c173260dd369d392661996278183eb56ec3c3d16951f915eedb6fc6c46c11d +size 3294108576 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_S.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_S.gguf new file mode 100644 index 0000000..9d58e60 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08df8d360b484e35b8a98f55ac50f78597de86aa45466c72f7570bd604b5fd23 +size 3256785824 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_XS.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ec94550 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2760646e9772abf48a22feda7b6af9886d8c0a8f19f2c9e8c20be26d7fac6b25 +size 3166395296 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ4_NL.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..4e27796 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c830778e8edf4420c9b789da0b018f09dfd8065cd96c7362c548f907de152d +size 4089994144 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ4_XS.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..4b0f5c6 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf1df063f7a0db0362f0688a30deaa1597094ff2b1f573ca89f0bbf1dd9e4ae +size 3895024544 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q2_K.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q2_K.gguf new file mode 100644 index 0000000..b2e4c85 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:394969621b24b90afcbb97617dcea5a6d5b7aa2d3f632f935e87dc8cb1986713 +size 2757319584 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_L.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..adbfd7f --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d91f16efac26b98b3e074e0703fff41dfbd800e4719f62c50e433ec40b2fcaf +size 3601996704 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_M.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..845fd3b --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c5c8fc4388a3d9a3204764d16f0cb254a25cd8fc88e77ea4152c310735e9b5d +size 3440909216 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_S.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c8651d7 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d2efffbfa957fce13ee53efae39c6a9758351457e61f03d45498932d2d6bfd +size 3251911584 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_0.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_0.gguf new file mode 100644 index 0000000..b2a83c1 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c681b396ea15c794811c79b9445a32ecf8a5b15c5d652299976cbdde19a84c41 +size 4093795232 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_1.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_1.gguf new file mode 100644 index 0000000..21bf70e --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b179b1cf665d2f09e777151ce757c39445141a06aaa779f9c9bf2fcc96b82637 +size 4477639584 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_K_M.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..3aee936 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b343bd818a14ff4a6dace8edbeb32640d501a9a6e56b7243ff08149cf406f0 +size 4237065120 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_K_S.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4cb7a46 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:130d0b51245b07c74febcb0892448011509fca5d5363adfa4bf6b962ccbb14fa +size 4102708128 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q5_K_M.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..43de3c9 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08cb26bcb3d029272a34b12f8af7e446b3da04f6df38ce6fe7d1522e4c237ee2 +size 4947999648 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q5_K_S.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..e0d037a --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1ed8059c727eb98794262a38566119c29c4d35df63ffd4e02a56792159aa71 +size 4869872544 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q6_K.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q6_K.gguf new file mode 100644 index 0000000..87fb281 --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7870cebf5d84a8bfdcdffdd219812767a8ac2d78de9bb912fae53f6da064cbbd +size 5703367584 diff --git a/MasriSwitch-Gemma3n-Transcriber-v1.imatrix.gguf b/MasriSwitch-Gemma3n-Transcriber-v1.imatrix.gguf new file mode 100644 index 0000000..2d99fed --- /dev/null +++ b/MasriSwitch-Gemma3n-Transcriber-v1.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f96b184711c5461a0b9038aada2aeded9e183a240bb2318613de575797d4d0b4 +size 4747936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fcae616 --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: oddadmix/MasriSwitch-Gemma3n-Transcriber-v1 +datasets: +- MohamedRashad/arabic-english-code-switching +language: +- en +- ar +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3n +- egyptian +- codeswitch +- arabic +- masry +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/oddadmix/MasriSwitch-Gemma3n-Transcriber-v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-GGUF + +**This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-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/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q2_K.gguf) | i1-Q2_K | 2.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_S.gguf) | i1-IQ3_S | 3.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q4_1.gguf) | i1-Q4_1 | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/MasriSwitch-Gemma3n-Transcriber-v1-i1-GGUF/resolve/main/MasriSwitch-Gemma3n-Transcriber-v1.i1-Q6_K.gguf) | i1-Q6_K | 5.8 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +