commit 80636568a3bbff7513302fdac57cfb0ca4c536d1 Author: ModelHub XC Date: Fri Jun 19 16:52:19 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Dolphin-2.8-slerp-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e558371 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +Dolphin-2.8-slerp.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dolphin-2.8-slerp.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Dolphin-2.8-slerp.i1-IQ1_M.gguf b/Dolphin-2.8-slerp.i1-IQ1_M.gguf new file mode 100644 index 0000000..8138f7e --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677d2e8eec11f809b908349049d619efd7ad2ef61b6a97a407a80f691bad72d4 +size 1754447392 diff --git a/Dolphin-2.8-slerp.i1-IQ1_S.gguf b/Dolphin-2.8-slerp.i1-IQ1_S.gguf new file mode 100644 index 0000000..93d4ac8 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60204293b9cba0a1528520057b188a3211e7d9368991419651549221150daf1 +size 1612103200 diff --git a/Dolphin-2.8-slerp.i1-IQ2_M.gguf b/Dolphin-2.8-slerp.i1-IQ2_M.gguf new file mode 100644 index 0000000..7e143dd --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c1d0447f470678db7f3ec27d928b48ca85a9dd22ee0a48af9ebabe41fece606 +size 2500714016 diff --git a/Dolphin-2.8-slerp.i1-IQ2_S.gguf b/Dolphin-2.8-slerp.i1-IQ2_S.gguf new file mode 100644 index 0000000..98ffa49 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:240002508c445a902f26d27992bc475229f749381d52ac568a84da75156da475 +size 2310921760 diff --git a/Dolphin-2.8-slerp.i1-IQ2_XS.gguf b/Dolphin-2.8-slerp.i1-IQ2_XS.gguf new file mode 100644 index 0000000..032f448 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ca43683fa2312f508c061de6b8e1e710f14cab90b9e27bde93a7766e91bcc4 +size 2198257184 diff --git a/Dolphin-2.8-slerp.i1-IQ2_XXS.gguf b/Dolphin-2.8-slerp.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ab10b39 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a67195c71a898f426bcbf64516c648d3f12979054e168610a81c10aff5b966cd +size 1991687712 diff --git a/Dolphin-2.8-slerp.i1-IQ3_M.gguf b/Dolphin-2.8-slerp.i1-IQ3_M.gguf new file mode 100644 index 0000000..7e84425 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb97c17faa337ca0912fe271b9f6a510a6ca878b743ed2efd68c1dc275d8715 +size 3284893216 diff --git a/Dolphin-2.8-slerp.i1-IQ3_S.gguf b/Dolphin-2.8-slerp.i1-IQ3_S.gguf new file mode 100644 index 0000000..5c03ade --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14ed99869be83fc2b90bc6f7bb25c704f4af87a4959d7594e74b6692cad176d7 +size 3182394912 diff --git a/Dolphin-2.8-slerp.i1-IQ3_XS.gguf b/Dolphin-2.8-slerp.i1-IQ3_XS.gguf new file mode 100644 index 0000000..2702ee2 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f79c0099d27cda4bbee160c99527c686bb8b6af581e7b2e3489f9166b4d08695 +size 3018817056 diff --git a/Dolphin-2.8-slerp.i1-IQ3_XXS.gguf b/Dolphin-2.8-slerp.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0485c79 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5129be68ff262484a106c3c783c9207cd75fe96d93b02482a85982971776fc27 +size 2827345440 diff --git a/Dolphin-2.8-slerp.i1-IQ4_XS.gguf b/Dolphin-2.8-slerp.i1-IQ4_XS.gguf new file mode 100644 index 0000000..62d5374 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989dafce1f4f13fc7897b150e85316d361470cc50e5a3c15adcf886e709d4f0b +size 3907690016 diff --git a/Dolphin-2.8-slerp.i1-Q2_K.gguf b/Dolphin-2.8-slerp.i1-Q2_K.gguf new file mode 100644 index 0000000..5031731 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:108440b16b4ccd9a0a8781dc44b86de557ddf67df4026d6b1ea86762abeb95c9 +size 2719243808 diff --git a/Dolphin-2.8-slerp.i1-Q2_K_S.gguf b/Dolphin-2.8-slerp.i1-Q2_K_S.gguf new file mode 100644 index 0000000..9f6b34f --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6b65a98256273cd4141957b7d584222a8fbb51b86457c4267e14e8a8d98989b +size 2528927264 diff --git a/Dolphin-2.8-slerp.i1-Q3_K_L.gguf b/Dolphin-2.8-slerp.i1-Q3_K_L.gguf new file mode 100644 index 0000000..96b8f70 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168aeef7005720c850b56be56e6a470ef2fce6c45972fc145833a7099b445c78 +size 3822026272 diff --git a/Dolphin-2.8-slerp.i1-Q3_K_M.gguf b/Dolphin-2.8-slerp.i1-Q3_K_M.gguf new file mode 100644 index 0000000..fd72a1e --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f6be72881057161356ecf22989946b6d1829095f8194f5e18463b77b049f68d +size 3518987808 diff --git a/Dolphin-2.8-slerp.i1-Q3_K_S.gguf b/Dolphin-2.8-slerp.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b2fc2e8 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6db7d99b9f8320c549decc410fc284ab220bf228a3d1cc8ffa24baec3235b882 +size 3164569120 diff --git a/Dolphin-2.8-slerp.i1-Q4_0.gguf b/Dolphin-2.8-slerp.i1-Q4_0.gguf new file mode 100644 index 0000000..95383be --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6c4dda32d34e6bf4fdbc071914c9b24cd1d36569e66b006efe36c7d9fcaa7c +size 4123598368 diff --git a/Dolphin-2.8-slerp.i1-Q4_K_M.gguf b/Dolphin-2.8-slerp.i1-Q4_K_M.gguf new file mode 100644 index 0000000..68fdebf --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:867ede511dfed5c854d2526da0045afd0ad0710b75569db643f510458e639663 +size 4368440864 diff --git a/Dolphin-2.8-slerp.i1-Q4_K_S.gguf b/Dolphin-2.8-slerp.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d3334f7 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9807a7b9894accaff14708e2eee6165645e5a28149211b8aa391aa140d4dd62d +size 4140375584 diff --git a/Dolphin-2.8-slerp.i1-Q5_K_M.gguf b/Dolphin-2.8-slerp.i1-Q5_K_M.gguf new file mode 100644 index 0000000..58f1b40 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b51fbf15903295de8f382e52bb74a0b806a9e3a661a23d8f9312991d56d3ce46 +size 5131410976 diff --git a/Dolphin-2.8-slerp.i1-Q5_K_S.gguf b/Dolphin-2.8-slerp.i1-Q5_K_S.gguf new file mode 100644 index 0000000..b67856d --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b76d14902418e52be060725f78e3936b11aa4d84da2885a6eccc30b89d43db +size 4997717536 diff --git a/Dolphin-2.8-slerp.i1-Q6_K.gguf b/Dolphin-2.8-slerp.i1-Q6_K.gguf new file mode 100644 index 0000000..50b5591 --- /dev/null +++ b/Dolphin-2.8-slerp.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63db076cba54984d7845735dc1fabe86e42a9368639b4b1cf66118fd88f3eb5f +size 5942066720 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dda0d31 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: pabloce/Dolphin-2.8-slerp +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation +- autotrain_compatible +- endpoints_compatible +- chatml +- text-generation-inference +- transformers +- slerp +- mistral +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/pabloce/Dolphin-2.8-slerp + + +static quants are available at https://huggingface.co/mradermacher/Dolphin-2.8-slerp-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/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Dolphin-2.8-slerp-i1-GGUF/resolve/main/Dolphin-2.8-slerp.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | 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..7ddc7d9 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39bc1f1167d7a8c290e3d08956c77eee462b675adf54d6f6a1fba7147662e405 +size 4988157