commit 33529153c444a7cc3bf5c403f35203666f8034cf Author: ModelHub XC Date: Sat Jun 20 01:44:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gamunu-4B-Instruct-Alpha-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..41bd2a2 --- /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 +Gamunu-4B-Instruct-Alpha.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gamunu-4B-Instruct-Alpha.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gamunu-4B-Instruct-Alpha.IQ4_XS.gguf b/Gamunu-4B-Instruct-Alpha.IQ4_XS.gguf new file mode 100644 index 0000000..f049191 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9570abe7e840cc9e6850eb3b7964bdb6ff8fad9fa38ce3979bee160b69bd68 +size 2279624960 diff --git a/Gamunu-4B-Instruct-Alpha.Q2_K.gguf b/Gamunu-4B-Instruct-Alpha.Q2_K.gguf new file mode 100644 index 0000000..d39f26a --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f6999935657148ce6398f930e1ed7a9c44162603ffa35468f386b7ed09cb887 +size 1729163520 diff --git a/Gamunu-4B-Instruct-Alpha.Q3_K_L.gguf b/Gamunu-4B-Instruct-Alpha.Q3_K_L.gguf new file mode 100644 index 0000000..3b0edc6 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36580a43fbe9a89bcbbd5f1114d91726ee8c9923483e9f3c28811adb9c97989e +size 2236084480 diff --git a/Gamunu-4B-Instruct-Alpha.Q3_K_M.gguf b/Gamunu-4B-Instruct-Alpha.Q3_K_M.gguf new file mode 100644 index 0000000..f61a913 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f01f72ac4d9eed84d9fc266fabbf117b4c04b174fa56b63a410eeaf9c50402a +size 2098458880 diff --git a/Gamunu-4B-Instruct-Alpha.Q3_K_S.gguf b/Gamunu-4B-Instruct-Alpha.Q3_K_S.gguf new file mode 100644 index 0000000..b7b8ac0 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31863765f7c87873cca431314cdc85ef9c2c2ea675b652be753dabdc8064eaaf +size 1937363200 diff --git a/Gamunu-4B-Instruct-Alpha.Q4_K_M.gguf b/Gamunu-4B-Instruct-Alpha.Q4_K_M.gguf new file mode 100644 index 0000000..3108aa8 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7aa15c4e8de49c16fe4fda8dbd275d31f6c88638376c64e670092f8a0800afc +size 2489893120 diff --git a/Gamunu-4B-Instruct-Alpha.Q4_K_S.gguf b/Gamunu-4B-Instruct-Alpha.Q4_K_S.gguf new file mode 100644 index 0000000..20640c7 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf7fc678d74509cba0f100d75e41417795a1e0e17a1d07872469c733b002d961 +size 2377928960 diff --git a/Gamunu-4B-Instruct-Alpha.Q5_K_M.gguf b/Gamunu-4B-Instruct-Alpha.Q5_K_M.gguf new file mode 100644 index 0000000..d53d3a5 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879916e346779522f4f11d74fda375c315e721d31e45ab009ec16b167e79c413 +size 2829697280 diff --git a/Gamunu-4B-Instruct-Alpha.Q5_K_S.gguf b/Gamunu-4B-Instruct-Alpha.Q5_K_S.gguf new file mode 100644 index 0000000..98c81c2 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93cf81ea2eca69aeefee98206db68ad2f52031696440818a404ea05219cce8fd +size 2764591360 diff --git a/Gamunu-4B-Instruct-Alpha.Q6_K.gguf b/Gamunu-4B-Instruct-Alpha.Q6_K.gguf new file mode 100644 index 0000000..358e526 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d80c60dc2c196745ab39e472e019e4410fd769f6c6fa39589f0bdfe8f38a53a6 +size 3190739200 diff --git a/Gamunu-4B-Instruct-Alpha.Q8_0.gguf b/Gamunu-4B-Instruct-Alpha.Q8_0.gguf new file mode 100644 index 0000000..ef1ceb3 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8397cb86396a1fbc2d3c3ade8266bd0824179a594aaf8773c536a4105195b60 +size 4130401280 diff --git a/Gamunu-4B-Instruct-Alpha.f16.gguf b/Gamunu-4B-Instruct-Alpha.f16.gguf new file mode 100644 index 0000000..628206b --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c939bb76720bc8430d56546a5bc403853170646009d406d1cfe3d9625dc590fd +size 7767802880 diff --git a/Gamunu-4B-Instruct-Alpha.mmproj-Q8_0.gguf b/Gamunu-4B-Instruct-Alpha.mmproj-Q8_0.gguf new file mode 100644 index 0000000..7e72430 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ac1501966815e3a5ff6fd746370aae44f4d29d5c042b2d9004fcd0232b66aa +size 591377952 diff --git a/Gamunu-4B-Instruct-Alpha.mmproj-f16.gguf b/Gamunu-4B-Instruct-Alpha.mmproj-f16.gguf new file mode 100644 index 0000000..1e83836 --- /dev/null +++ b/Gamunu-4B-Instruct-Alpha.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4522df5ed223f602c081d94b8631b9d86d601a6f1a825cdfb2d33dfbd1891340 +size 851251872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..06b485a --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: manthilaffs/Gamunu-4B-Instruct-Alpha +language: +- si +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- instruction-following +- NLP +- question-answering +- reasoning +- academic +- maths +- LK +--- +## About + + + + + + + + + +static quants of https://huggingface.co/manthilaffs/Gamunu-4B-Instruct-Alpha + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gamunu-4B-Instruct-Alpha-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-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/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gamunu-4B-Instruct-Alpha-GGUF/resolve/main/Gamunu-4B-Instruct-Alpha.f16.gguf) | f16 | 7.9 | 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. + +