commit 3cf19fa366fdb852300dc773df9128747a3d8d1e Author: ModelHub XC Date: Sun Sep 20 12:24:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7634562 --- /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 +EXAONESumm-3.0-7.8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONESumm-3.0-7.8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/EXAONESumm-3.0-7.8B-Instruct.IQ4_XS.gguf b/EXAONESumm-3.0-7.8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..ae9a688 --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afef2ac822f801e4d79390ad4016d4ec5ff0953140797223d31700c79e36c13c +size 4337588064 diff --git a/EXAONESumm-3.0-7.8B-Instruct.Q2_K.gguf b/EXAONESumm-3.0-7.8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..26a5cb4 --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7cddcd35c3c020cf3a6469cdc60b08c066a5fc158f71e792c460e0d37ba575c +size 3053868896 diff --git a/EXAONESumm-3.0-7.8B-Instruct.Q3_K_L.gguf b/EXAONESumm-3.0-7.8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..4daeaab --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95f5e0c6637669627b87ae55ce7db5fbc2f7855cf2565adbb62a9c7fcb9b7f85 +size 4185937760 diff --git a/EXAONESumm-3.0-7.8B-Instruct.Q3_K_M.gguf b/EXAONESumm-3.0-7.8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..458b399 --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1b83cf9388548641163a35d1b11d65127456bd549115f8a15302bd9110e4e1a +size 3882899296 diff --git a/EXAONESumm-3.0-7.8B-Instruct.Q3_K_S.gguf b/EXAONESumm-3.0-7.8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..1868d49 --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:569ec05919bfdad9114c7764cc2f70646ad558506fda4e7bf05e48bf4276d237 +size 3528480608 diff --git a/EXAONESumm-3.0-7.8B-Instruct.Q4_K_M.gguf b/EXAONESumm-3.0-7.8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..53292c6 --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab704a731b2c10dd956149d53ba8ac453201527b9a5deab4ac22ec716c2831b7 +size 4770649952 diff --git a/EXAONESumm-3.0-7.8B-Instruct.Q4_K_S.gguf b/EXAONESumm-3.0-7.8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..b386353 --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3531e4a1e3b4f84c9b8fe4a8dc9f20f66c0cd65cdf004a910a396bd6afcf4154 +size 4542584672 diff --git a/EXAONESumm-3.0-7.8B-Instruct.Q5_K_M.gguf b/EXAONESumm-3.0-7.8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..018b83a --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd85f208b1db4154650a926fe0c2ff1c325c62ea0a2f0f0f074942b9ff8f164 +size 5569664864 diff --git a/EXAONESumm-3.0-7.8B-Instruct.Q5_K_S.gguf b/EXAONESumm-3.0-7.8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..c061955 --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63ddad3c86113267cd85981989fa15bcf1e75432f86bb6ea70796a78dc273e5d +size 5435971424 diff --git a/EXAONESumm-3.0-7.8B-Instruct.Q6_K.gguf b/EXAONESumm-3.0-7.8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..42272a9 --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba6de988b6b3ac61737aa7f83a4a16a3dd28cccf660b212df7ef89a2994ffc8 +size 6418618208 diff --git a/EXAONESumm-3.0-7.8B-Instruct.Q8_0.gguf b/EXAONESumm-3.0-7.8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..276d724 --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f76136c3360215d549acacf2b08bfa84710480fdd1cca7cb7d1b774e1aabedba +size 8312084320 diff --git a/EXAONESumm-3.0-7.8B-Instruct.f16.gguf b/EXAONESumm-3.0-7.8B-Instruct.f16.gguf new file mode 100644 index 0000000..6c03921 --- /dev/null +++ b/EXAONESumm-3.0-7.8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09abdc3fd76575de04d9c85ec45839dddae16a602210204246d3f4840c82b91 +size 15641630560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..789ec94 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: fiveflow/EXAONESumm-3.0-7.8B-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/fiveflow/EXAONESumm-3.0-7.8B-Instruct + + +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/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.Q6_K.gguf) | Q6_K | 6.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.Q8_0.gguf) | Q8_0 | 8.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONESumm-3.0-7.8B-Instruct-GGUF/resolve/main/EXAONESumm-3.0-7.8B-Instruct.f16.gguf) | f16 | 15.7 | 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. + +