commit 0004100c5da182216f887c8fbc68aff0a0978e26 Author: ModelHub XC Date: Mon May 11 14:10:46 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/EXAONE-Deep-7.8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c80e11c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-Deep-7.8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/EXAONE-Deep-7.8B.i1-IQ1_M.gguf b/EXAONE-Deep-7.8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..73ab7fa --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6819f527c607ba9cf361f64c8c309a09625cf06d95046e967be8feca0def12e +size 2050776032 diff --git a/EXAONE-Deep-7.8B.i1-IQ1_S.gguf b/EXAONE-Deep-7.8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..5b4035c --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9783cba1351c9b868da824ef20fc4398241f820c6813d9dc9ce630f95598daee +size 1908431840 diff --git a/EXAONE-Deep-7.8B.i1-IQ2_M.gguf b/EXAONE-Deep-7.8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..fe04d7a --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b8fd8b8534d571db9542a56a1eb54832a30b5a423ae2e94b8d8f13cc9282da +size 2826329056 diff --git a/EXAONE-Deep-7.8B.i1-IQ2_S.gguf b/EXAONE-Deep-7.8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..82acf9d --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87fc6c9b8b511942a40a0922258568ca0526b532744c778395969a1c06008a57 +size 2636536800 diff --git a/EXAONE-Deep-7.8B.i1-IQ2_XS.gguf b/EXAONE-Deep-7.8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3f206a0 --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582a36ef31b91b7212e6f1724d542cecdb04f058d8c1c092fa9507022d68438d +size 2494585824 diff --git a/EXAONE-Deep-7.8B.i1-IQ2_XXS.gguf b/EXAONE-Deep-7.8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ba093ca --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2437112ad337aa8f36475ad2ca320f6c9e66404df5b0aa9ec8acd46758f77c54 +size 2288016352 diff --git a/EXAONE-Deep-7.8B.i1-IQ3_M.gguf b/EXAONE-Deep-7.8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..0a3d449 --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bccf097db53fbf5eec28be6ddd8106c9a75cbf9f1005a2064563f8a3cafa1e7c +size 3648805856 diff --git a/EXAONE-Deep-7.8B.i1-IQ3_S.gguf b/EXAONE-Deep-7.8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..407ef27 --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8870b086102ada552d370021078651f751be3b624c21c3d609c35b7aabb9bc5a +size 3546307552 diff --git a/EXAONE-Deep-7.8B.i1-IQ3_XS.gguf b/EXAONE-Deep-7.8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f056e37 --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06a41a2fed8e78abbfe38c27685e6b9712e398e5488f6c78765fe66ce5109977 +size 3382729696 diff --git a/EXAONE-Deep-7.8B.i1-IQ3_XXS.gguf b/EXAONE-Deep-7.8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f1bd4bd --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43bd3f9446e615891577f212314c418bc309a80ba38fc389fec0699c7f0ce7af +size 3152960480 diff --git a/EXAONE-Deep-7.8B.i1-IQ4_NL.gguf b/EXAONE-Deep-7.8B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..a34c732 --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc4eb40e2cc5ee77f090932f6955f61b20fd5a0f660da674e4182f85b09712fe +size 4527905760 diff --git a/EXAONE-Deep-7.8B.i1-IQ4_XS.gguf b/EXAONE-Deep-7.8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..aa16663 --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:822698a48798b51ee941229da2b8ff9b9f3003edad4885663572b3b7aa8c1c7e +size 4300889056 diff --git a/EXAONE-Deep-7.8B.i1-Q2_K.gguf b/EXAONE-Deep-7.8B.i1-Q2_K.gguf new file mode 100644 index 0000000..a2238ce --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1a34f3daaaf003f1bd309f58790c0b27da35a3b39a3a8f9f5a50104bbcab62 +size 3053870048 diff --git a/EXAONE-Deep-7.8B.i1-Q2_K_S.gguf b/EXAONE-Deep-7.8B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..bdcf8a2 --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ad09fcbbd8a2fb0de5186af2d261b10206a478dfaa3cc12483bde307255897b +size 2863553504 diff --git a/EXAONE-Deep-7.8B.i1-Q3_K_L.gguf b/EXAONE-Deep-7.8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8702cca --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea71ad427b89068b64fcd663fea0312286764677d121545c3a85c0ac604ee73e +size 4185938912 diff --git a/EXAONE-Deep-7.8B.i1-Q3_K_M.gguf b/EXAONE-Deep-7.8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..54a432a --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:783993c342b6a45cc13926fdd749d4595fb2f613bc3d5b75b8280a8b023c0533 +size 3882900448 diff --git a/EXAONE-Deep-7.8B.i1-Q3_K_S.gguf b/EXAONE-Deep-7.8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3a43e6e --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6546fd14f01490a71240d6697aadac7f2ec069407d7aa4a2babc8d793ec4c166 +size 3528481760 diff --git a/EXAONE-Deep-7.8B.i1-Q4_0.gguf b/EXAONE-Deep-7.8B.i1-Q4_0.gguf new file mode 100644 index 0000000..a503625 --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ea3f48d8dc52f777581575a47420d0a5231f0c8e3c5c66158a1087bef74b30 +size 4525808608 diff --git a/EXAONE-Deep-7.8B.i1-Q4_1.gguf b/EXAONE-Deep-7.8B.i1-Q4_1.gguf new file mode 100644 index 0000000..227269f --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68623da7ad48eabb4f1436154756881dea714707f75212e922bfa12900dc67a +size 4973550560 diff --git a/EXAONE-Deep-7.8B.i1-Q4_K_M.gguf b/EXAONE-Deep-7.8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..797668b --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9422a29b4a3001478c011347076239b53416f4795c3f5718e5fe9067be0fb7a +size 4770651104 diff --git a/EXAONE-Deep-7.8B.i1-Q4_K_S.gguf b/EXAONE-Deep-7.8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..799eeb8 --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b25656b1da22d562bd56f65b5e0e83d7836425d6cd514bba6591408f03f3a4e +size 4542585824 diff --git a/EXAONE-Deep-7.8B.i1-Q5_K_M.gguf b/EXAONE-Deep-7.8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7147e62 --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:499bde6559095836855e69b972b0e189dcda728919f7235fc5851a00b7fb3f8b +size 5569666016 diff --git a/EXAONE-Deep-7.8B.i1-Q5_K_S.gguf b/EXAONE-Deep-7.8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..652677e --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d8de462b38d0e5b9e6766981cafdaa841be30c22172a5de6550863a5177f2a2 +size 5435972576 diff --git a/EXAONE-Deep-7.8B.i1-Q6_K.gguf b/EXAONE-Deep-7.8B.i1-Q6_K.gguf new file mode 100644 index 0000000..598527d --- /dev/null +++ b/EXAONE-Deep-7.8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd2b170a7feedbe0eaf384bbdb7022b3e033b62eabb513e658537405b6a34a2 +size 6418619360 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b7f4384 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: LGAI-EXAONE/EXAONE-Deep-7.8B +language: +- en +- ko +library_name: transformers +license: other +license_link: LICENSE +license_name: exaone +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- lg-ai +- exaone +- exaone-deep +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/LGAI-EXAONE/EXAONE-Deep-7.8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#EXAONE-Deep-7.8B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-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/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.0 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q2_K.gguf) | i1-Q2_K | 3.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q4_1.gguf) | i1-Q4_1 | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/EXAONE-Deep-7.8B-i1-GGUF/resolve/main/EXAONE-Deep-7.8B.i1-Q6_K.gguf) | i1-Q6_K | 6.5 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..1a0da76 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1feee35462722ecebe9e6752148ca0b2fc1fa58aa2b4e2ad6ad05a425c4a5376 +size 4988157