commit c5e30deb3f769370fda55ff0de81028be1626e23 Author: ModelHub XC Date: Sun Aug 23 13:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BanglaMath-llama-ShortQ-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c86faf8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +BanglaMath-llama-ShortQ.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BanglaMath-llama-ShortQ.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BanglaMath-llama-ShortQ.IQ4_XS.gguf b/BanglaMath-llama-ShortQ.IQ4_XS.gguf new file mode 100644 index 0000000..458b8a2 --- /dev/null +++ b/BanglaMath-llama-ShortQ.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9aea292dea0a2538877f94cf2e45ad632fe8026d328aa203441131d50f998b +size 1840904576 diff --git a/BanglaMath-llama-ShortQ.Q2_K.gguf b/BanglaMath-llama-ShortQ.Q2_K.gguf new file mode 100644 index 0000000..fcbba4b --- /dev/null +++ b/BanglaMath-llama-ShortQ.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47effa75882368ce10537dfe5c923fb16f06553510d7e9871b2a80e06c0ea2a0 +size 1363933568 diff --git a/BanglaMath-llama-ShortQ.Q3_K_L.gguf b/BanglaMath-llama-ShortQ.Q3_K_L.gguf new file mode 100644 index 0000000..16ee460 --- /dev/null +++ b/BanglaMath-llama-ShortQ.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f6ee476da11b6df9ce63788924e4babb6d0b243cc859dec2056c74af305d153 +size 1815345536 diff --git a/BanglaMath-llama-ShortQ.Q3_K_M.gguf b/BanglaMath-llama-ShortQ.Q3_K_M.gguf new file mode 100644 index 0000000..c76aca2 --- /dev/null +++ b/BanglaMath-llama-ShortQ.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c80d4b3dc57972985b5ef1e7d8a5c24fd051bc0bd53199e7faeaa5d28d04d9 +size 1687157120 diff --git a/BanglaMath-llama-ShortQ.Q3_K_S.gguf b/BanglaMath-llama-ShortQ.Q3_K_S.gguf new file mode 100644 index 0000000..779c3cd --- /dev/null +++ b/BanglaMath-llama-ShortQ.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b19d4bf951646c8719bf4991da307a9c5e05f140e6a39703e8ea13ef45305204 +size 1542846848 diff --git a/BanglaMath-llama-ShortQ.Q4_K_M.gguf b/BanglaMath-llama-ShortQ.Q4_K_M.gguf new file mode 100644 index 0000000..51caafb --- /dev/null +++ b/BanglaMath-llama-ShortQ.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:778b9ac88af17abbba8490b46caf70ced68a81c49adbbfc3fa08f3c9588fb5c2 +size 2019375488 diff --git a/BanglaMath-llama-ShortQ.Q4_K_S.gguf b/BanglaMath-llama-ShortQ.Q4_K_S.gguf new file mode 100644 index 0000000..e7a50e6 --- /dev/null +++ b/BanglaMath-llama-ShortQ.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a541411d10d55406ca56cd66c7f69afaf370d3d9be8fa109a367f98e8d682bb +size 1928198528 diff --git a/BanglaMath-llama-ShortQ.Q5_K_M.gguf b/BanglaMath-llama-ShortQ.Q5_K_M.gguf new file mode 100644 index 0000000..854f0ac --- /dev/null +++ b/BanglaMath-llama-ShortQ.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6c6d38b5cf8617a66dbf1297bcfbd15c1533a52581ff52358aea5c506b0718 +size 2322151808 diff --git a/BanglaMath-llama-ShortQ.Q5_K_S.gguf b/BanglaMath-llama-ShortQ.Q5_K_S.gguf new file mode 100644 index 0000000..7fb9a7d --- /dev/null +++ b/BanglaMath-llama-ShortQ.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b20e07fca03f371185d6350808bfb21d00ed360f7995e916da80b0b8110773 +size 2269510016 diff --git a/BanglaMath-llama-ShortQ.Q6_K.gguf b/BanglaMath-llama-ShortQ.Q6_K.gguf new file mode 100644 index 0000000..bdcf1f0 --- /dev/null +++ b/BanglaMath-llama-ShortQ.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:189ead0e3ab1fb542ab52a059a2593adb260a9dee2126f939f34e2f9ae5089cf +size 2643851648 diff --git a/BanglaMath-llama-ShortQ.Q8_0.gguf b/BanglaMath-llama-ShortQ.Q8_0.gguf new file mode 100644 index 0000000..21ef5ad --- /dev/null +++ b/BanglaMath-llama-ShortQ.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4b178622005b0b1fb279c7bc3e7ad12841b9b1e2e3bf005209bba5614a80149 +size 3421897088 diff --git a/BanglaMath-llama-ShortQ.f16.gguf b/BanglaMath-llama-ShortQ.f16.gguf new file mode 100644 index 0000000..4d6ae8e --- /dev/null +++ b/BanglaMath-llama-ShortQ.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928573a673e463e37387d1b32bc54d1c32a297161c895c932b4e8cca9a9f7837 +size 6433685888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e5105af --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: nayemislamzr/BanglaMath-llama-ShortQ +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/nayemislamzr/BanglaMath-llama-ShortQ + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BanglaMath-llama-ShortQ-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/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BanglaMath-llama-ShortQ-GGUF/resolve/main/BanglaMath-llama-ShortQ.f16.gguf) | f16 | 6.5 | 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. + +